© 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. 42465
    Prev
    Next
    INDEX
    Explanations

    variety of hits

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

    The neuron fires on occurrences of the token “hits” (including its Spanish spelling “itos”), as when listing hit counts or greatest‐hits in album data.

    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
    ed
    -2.81
    <
    -2.66
    *
    -2.47
    <td>
    -2.42
    '
    -2.34
     We
    -2.13
     “
    -2.11
    <i>
    -2.11
     двох
    -2.09
     dieses
    -2.08
    POSITIVE LOGITS
     hits
    2.73
    ︓
    2.70
    蠖
    2.45
    Ꮞ
    2.39
    噐
    2.33
    〮
    2.31
    Hits
    2.27
    
    2.25
    hits
    2.16
    pulseira
    2.16
    Activations Density 0.002%

    No Known Activations