© 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. 130025
    Prev
    Next
    INDEX
    Explanations

    proximity

    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
     stato
    -2.69
    諍
    -2.22
    <bos>
    -2.19
    蘗
    -2.11
    ти
    -2.05
    である
    -1.98
    馴
    -1.98
     района
    -1.96
    柵
    -1.96
    rierten
    -1.94
    POSITIVE LOGITS
     the
    3.64
     They
    3.11
     Their
    3.09
    を行い
    2.56
    うまい
    2.53
    禇
    2.52
     telah
    2.30
     estrena
    2.25
     nuovi
    2.23
     verhind
    2.23
    Activations Density 0.015%

    No Known Activations