© 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. 22-GEMMASCOPE-RES-131K
    7. 26808
    Prev
    Next
    INDEX
    Explanations

    script tags and includes

    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_22/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
    xmm
    -0.90
     trámite
    -0.88
    })_{
    -0.86
     jota
    -0.86
     each
    -0.86
    ngOn
    -0.85
     wirklich
    -0.84
    ङ
    -0.84
    iframe
    -0.84
    iterate
    -0.83
    POSITIVE LOGITS
     then
    1.22
     사용
    1.01
    での
    0.97
    额头
    0.90
    ängerin
    0.89
    并在
    0.88
     vervolgens
    0.86
    แล้ว
    0.82
    abetta
    0.82
    гы
    0.81
    Activations Density 0.048%

    No Known Activations