© 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. 10-GEMMASCOPE-RES-131K
    7. 3644
    Prev
    Next
    INDEX
    Explanations

    ascribed to / including / package

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

    This neuron strongly activates on the token “ascribed,” i.e. it detects occurrences of that specific word.

    oai_token-act-pair · o4-miniTriggered 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
    他們的
    -2.53
    を行い
    -2.42
    独特的
    -2.41
     visitó
    -2.36
     Fotografía
    -2.34
    反复
    -2.34
    もしっかり
    -2.30
    淠
    -2.30
     respondió
    -2.25
     tetapi
    -2.22
    POSITIVE LOGITS
    ).
    3.06
    on
    3.03
    ed
    2.81
    *
    2.70
    na
    2.69
    恫
    2.56
    as
    2.53
    z
    2.52
    th
    2.45
    十八
    2.45
    Activations Density 0.005%

    No Known Activations