© 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. 163419
    Prev
    Next
    INDEX
    Explanations

    resides, vacant, duties, cellar, stunning

    np_acts-logits-general · gemini-2.5-flash-lite

    Agile developer

    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
    礦
    0.54
    ელი
    0.52
    т
    0.52
    uš
    0.50
    囉
    0.50
    ALAR
    0.49
    嘍
    0.48
    SELS
    0.47
     додат
    0.46
    ALA
    0.46
    POSITIVE LOGITS
     resides
    0.44
     legais
    0.44
     hardcore
    0.43
     releg
    0.42
     litig
    0.42
     =-\
    0.41
     断
    0.41
     />;
    0.41
     lesion
    0.41
     dy
    0.40
    Activations Density 0.001%

    No Known Activations