© 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. 25644
    Prev
    Next
    INDEX
    Explanations

    code blocks with braces and semicolons

    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
     Autó
    -1.03
     METHODOLOGY
    -0.90
     Minangkabau
    -0.89
     bruja
    -0.88
    作战
    -0.86
    无论
    -0.86
     Tooltip
    -0.85
    ﯿ
    -0.85
     consists
    -0.84
     aurez
    -0.83
    POSITIVE LOGITS
    亮点
    1.05
    蝠
    0.94
    rierten
    0.92
    Aly
    0.88
    蛟
    0.87
    instancetype
    0.86
    我对
    0.86
     branched
    0.86
    ión
    0.85
    ítő
    0.85
    Activations Density 0.004%

    No Known Activations