© 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. 765
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps

    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
     []:
    -1.74
    ();
    -1.69
    randrange
    -1.68
    Ţ
    -1.62
     if
    -1.59
    нологи
    -1.59
    )">
    -1.57
    if
    -1.52
    ;
    -1.52
    aughter
    -1.52
    POSITIVE LOGITS
     decoradas
    1.65
     decorados
    1.56
    说过
    1.51
    沨
    1.48
     continuamente
    1.43
     esfuer
    1.42
    畢竟
    1.41
    所说
    1.38
    .
    1.38
     plásticos
    1.37
    Activations Density 0.032%

    No Known Activations