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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 629
    Prev
    Next
    INDEX
    Explanations

    chief of X

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ?
    -2.83
    .
    -2.42
    ."
    -2.19
    </h3>
    -2.17
    e
    -2.09
    ,”
    -2.02
    ↵↵
    -1.98
    -
    -1.92
    ";
    -1.88
    正文
    -1.86
    POSITIVE LOGITS
    詎
    2.44
     esigen
    2.41
     paura
    2.36
     necessità
    2.30
    genodigd
    2.27
    嚒
    2.22
     voglia
    2.19
     lontano
    2.19
    嵛
    2.17
     intervento
    2.16
    Activations Density 0.003%

    No Known Activations