© 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. 254941
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    অর্থাৎ
    0.52
    <unused58>
    0.50
     एक्सरसा
    0.46
    ଐ
    0.46
    <unused83>
    0.44
     renderEncoder
    0.43
    <unused27>
    0.43
    すなわち
    0.43
    <unused85>
    0.42
    এখানে
    0.42
    POSITIVE LOGITS
    m
    0.47
     Tast
    0.46
    sa
    0.45
    тент
    0.45
    dob
    0.44
     Doh
    0.44
    和
    0.43
    вут
    0.43
     Dost
    0.43
    льм
    0.42
    Activations Density 0.000%

    No Known Activations