© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 134890
    Prev
    Next
    INDEX
    Explanations

    adding, setting, starting, pieces, piping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    excellent
    0.44
    PLUS
    0.43
    ស្ល
    0.39
    ALSO
    0.39
    occasion
    0.39
    $=\
    0.39
    QC
    0.39
     Hinweis
    0.39
    KILL
    0.39
    SHALL
    0.39
    POSITIVE LOGITS
    无论是
    0.47
     for
    0.46
     sys
    0.46
     metrics
    0.46
     gripe
    0.46
     compras
    0.45
     mip
    0.44
     「
    0.43
     npm
    0.43
     我们
    0.43
    Activations Density 0.001%

    No Known Activations