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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118445
    Prev
    Next
    INDEX
    Explanations

    Note: Microsoft Graph APIs

    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
    jaman
    -0.83
    commented
    -0.76
     commented
    -0.73
    汚れ
    -0.73
    presse
    -0.70
    怆
    -0.69
    ilane
    -0.68
    婴
    -0.68
    noticed
    -0.67
    нят
    -0.67
    POSITIVE LOGITS
     гу
    0.71
    ŚĆ
    0.68
     Survi
    0.67
     airborne
    0.67
    恭
    0.67
     aval
    0.66
    arar
    0.65
    鮒
    0.65
     fun
    0.65
     ey
    0.65
    Activations Density 0.051%

    No Known Activations