© 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. 66936
    Prev
    Next
    INDEX
    Explanations

    requires something

    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
     they
    -1.49
     своей
    -1.24
     \
    -1.23
     didn
    -1.21
     ihnen
    -1.18
     они
    -1.17
    ↵
    -1.16
    they
    -1.13
     there
    -1.12
     still
    -1.12
    POSITIVE LOGITS
     to
    2.52
     другому
    1.39
     Similar
    1.36
    同样的
    1.34
     būti
    1.33
    ากาศ
    1.32
    無い
    1.31
     another
    1.30
    );
    1.29
    наче
    1.29
    Activations Density 0.115%

    No Known Activations