© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65118
    Prev
    Next
    INDEX
    Explanations

    quotations and specific numbers

    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_34/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
    gefunden
    -0.83
    IZABETH
    -0.83
    blumen
    -0.79
     quarterback
    -0.78
    OuterClass
    -0.77
    ƣ
    -0.77
    hindu
    -0.77
     racconta
    -0.77
    lyon
    -0.76
     fucking
    -0.75
    POSITIVE LOGITS
     lợi
    0.78
     aceea
    0.77
     begle
    0.76
    واعد
    0.76
    ění
    0.75
    为
    0.73
    Odkazy
    0.72
    ;
    0.71
    ¢
    0.71
    gust
    0.70
    Activations Density 0.006%

    No Known Activations