© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44114
    Prev
    Next
    INDEX
    Explanations

    Amanda followed by a name or description

    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
    🪢
    -2.92
     prioridades
    -2.84
    しちゃ
    -2.69
    ।
    -2.61
    絨
    -2.58
    責任
    -2.58
    ☫
    -2.58
    綵
    -2.48
    後記
    -2.41
    。
    -2.41
    POSITIVE LOGITS
    e
    3.63
    k
    3.50
    i
    3.06
    C
    2.94
    s
    2.81
    ING
    2.80
    P
    2.72
    .
    2.69
    </strong>
    2.64
     formando
    2.55
    Activations Density 0.001%

    No Known Activations