© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92060
    Prev
    Next
    INDEX
    Explanations

    multi-lingual name prefixes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is highly sensitive to the initial subword of multi‐subword proper nouns (especially geographic/place names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Finnish language text, particularly Finnish names, locations, and words.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of Finnish (and sometimes Estonian) names and place-related proper nouns, especially capitalized subword chunks typical of those languages.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frauen
    -0.92
    たって
    -0.90
    と感じ
    -0.86
    渥
    -0.85
     Grüßen
    -0.85
     mato
    -0.84
    鍼
    -0.84
    Bli
    -0.84
    详解
    -0.84
     fett
    -0.83
    POSITIVE LOGITS
     vernünf
    0.94
    isenberg
    0.94
    Pues
    0.88
    NOTE
    0.85
    ときに
    0.85
     的
    0.85
    Nazionale
    0.84
     inaczej
    0.84
    NLS
    0.83
    ndes
    0.83
    Activations Density 0.006%

    No Known Activations