© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35202
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
    ON
    -0.92
     многие
    -0.91
    如果
    -0.90
     certain
    -0.87
    ОН
    -0.83
    нали
    -0.82
     intelek
    -0.82
    Emb
    -0.82
    EMBER
    -0.81
    곡
    -0.81
    POSITIVE LOGITS
     巷
    1.04
    块钱
    1.03
    govina
    0.99
    zamos
    0.96
    多少钱
    0.93
     $+\
    0.92
    具体的な
    0.92
    可以让
    0.91
    Unidad
    0.90
    喜歡的
    0.90
    Activations Density 0.002%

    No Known Activations