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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35926
    Prev
    Next
    INDEX
    Explanations

    names followed by related nouns

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

    The neuron fires on content-heavy tokens such as proper names, specialized terms, and technical nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Neden
    -1.00
     رغم
    -0.96
     Meski
    -0.93
    Sodium
    -0.93
    Meski
    -0.85
    Ibn
    -0.85
    もし
    -0.85
     atlik
    -0.84
    Pregnancy
    -0.83
     cercle
    -0.83
    POSITIVE LOGITS
     will
    1.08
    estión
    0.98
     fatta
    0.96
     its
    0.95
     could
    0.94
    dov
    0.90
     kecelakaan
    0.87
    ><?
    0.85
    vosti
    0.84
    껄
    0.84
    Activations Density 0.272%

    No Known Activations