© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 118909
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns

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

    The neuron activates on capitalized tokens that are proper names or other standalone named entities.

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

    foreign-language tokens and uncommon proper names or symbols, especially non-English text and unusual character sequences.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    proper nouns, particularly non-English personal names and place names.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     "
    -3.06
     estrictamente
    -2.86
     muchísimo
    -2.73
     "'
    -2.59
     ("
    -2.59
    蝎
    -2.58
     vuestro
    -2.56
    TintMode
    -2.55
     ampliamente
    -2.55
     fís
    -2.53
    POSITIVE LOGITS
    '
    3.14
    “
    3.05
    3
    3.03
    }
    2.92
    1
    2.83
    6
    2.58
    9
    2.53
    8
    2.48
    5
    2.42
    selben
    2.36
    Activations Density 0.329%

    No Known Activations