© 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. 128401
    Prev
    Next
    INDEX
    Explanations

    overstated, too, underestimate, Q:, How, Nemed

    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
     to
    -1.95
    "..."
    -1.51
     getToken
    -1.43
     by
    -1.38
     with
    -1.35
     in
    -1.32
     unless
    -1.30
     refuses
    -1.30
     sends
    -1.30
    NRAS
    -1.30
    POSITIVE LOGITS
     these
    1.45
     zwłaszcza
    1.41
     how
    1.41
     Bereichen
    1.36
    ↵
    1.34
    These
    1.33
     täglichen
    1.33
     این
    1.28
     correctamente
    1.26
     praktischen
    1.24
    Activations Density 0.003%

    No Known Activations