© 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. 85382
    Prev
    Next
    INDEX
    Explanations

    amount of

    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
     not
    -1.48
     parseFrom
    -1.46
     firebaseConfig
    -1.42
    hört
    -1.38
     belangrijke
    -1.38
    镦
    -1.38
     wholeheartedly
    -1.37
     prominently
    -1.34
     for
    -1.33
    িতে
    -1.33
    POSITIVE LOGITS
    푆
    1.67
    t
    1.54
    <bos>
    1.45
    <
    1.34
     Darüber
    1.31
     toreb
    1.30
    很快就
    1.27
     NACIONAL
    1.27
     thing
    1.23
    tagena
    1.23
    Activations Density 0.015%

    No Known Activations