© 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. 85209
    Prev
    Next
    INDEX
    Explanations

    an example of

    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
    ೣ
    -1.73
    我也
    -1.73
    了出来
    -1.69
    自殺
    -1.63
    縞
    -1.63
    ſſen
    -1.63
    〢
    -1.63
    齪
    -1.58
                
    -1.57
    HttpConnection
    -1.57
    POSITIVE LOGITS
    u
    2.17
     what
    1.77
    ことから
    1.72
    ጵ
    1.68
    on
    1.58
     “
    1.56
     uphold
    1.55
    異なる
    1.53
    꽂
    1.52
    後で
    1.51
    Activations Density 0.024%

    No Known Activations