© 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. 77161
    Prev
    Next
    INDEX
    Explanations

    dates and events

    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
    Ⅽ
    -0.84
     október
    -0.83
     افتراض
    -0.72
    を抜
    -0.70
     عبد
    -0.69
    brać
    -0.69
    september
    -0.68
    aleb
    -0.68
     September
    -0.67
    偈
    -0.66
    POSITIVE LOGITS
    JUNE
    0.79
    oxy
    0.77
     Haziran
    0.75
    ред
    0.73
     خرد
    0.72
    Easter
    0.71
    antas
    0.70
    idados
    0.70
     Inhibit
    0.70
    Pec
    0.69
    Activations Density 0.097%

    No Known Activations