© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129216
    Prev
    Next
    INDEX
    Explanations

    John or Giovanni

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

    The neuron activates on Bible Scripture references (book names like “John” plus chapter and verse numbers).

    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
    ”
    -2.08
    uggets
    -1.76
     halben
    -1.63
     continuar
    -1.62
     wenigen
    -1.57
     eigentlichen
    -1.55
    リンゴ
    -1.55
    _
    -1.53
    {
    -1.51
    ’
    -1.51
    POSITIVE LOGITS
    ௅
    1.95
    OUTUBE
    1.85
    providedIn
    1.85
     }));
    1.72
    __))
    1.71
    soever
    1.63
    Ꮉ
    1.62
    ]){
    1.61
    蒟
    1.60
    ());
    1.58
    Activations Density 0.022%

    No Known Activations