© 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. 67697
    Prev
    Next
    INDEX
    Explanations

    vector component magnitude

    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
    謦
    -1.43
     MINUTES
    -1.36
    裢
    -1.32
    菝
    -1.31
    阻止
    -1.26
     REALLY
    -1.26
    BRID
    -1.23
    .
    -1.20
    heren
    -1.20
    ErrUnexpectedEOF
    -1.20
    POSITIVE LOGITS
     four
    1.88
     from
    1.77
     three
    1.71
     both
    1.59
     at
    1.53
     without
    1.50
     two
    1.38
     in
    1.30
     several
    1.27
     the
    1.26
    Activations Density 0.042%

    No Known Activations