© 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. 246509
    Prev
    Next
    INDEX
    Explanations

    phone, Italians, Grit, dump, opportunity

    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
    egna
    0.53
    ome
    0.48
     再
    0.46
    emore
    0.45
    ｉ
    0.45
    i
    0.44
    openList
    0.44
    ization
    0.43
    ف
    0.43
    apping
    0.43
    POSITIVE LOGITS
     couplers
    0.48
     assume
    0.48
     receptacles
    0.46
     tecnolog
    0.45
    暧
    0.45
     frosty
    0.45
     émissions
    0.44
     imposs
    0.44
     legais
    0.44
     amaze
    0.43
    Activations Density 0.001%

    No Known Activations