© 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. 121363
    Prev
    Next
    INDEX
    Explanations

    sole discretion

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

    historical events and technical systems

    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
    躹
    0.50
     Compet
    0.49
     قدر
    0.48
     tı
    0.48
    ין
    0.46
     Très
    0.45
     '|')
    0.45
     Muy
    0.45
    خواه
    0.44
     sash
    0.44
    POSITIVE LOGITS
    asih
    0.49
    ровал
    0.48
    err
    0.46
    ai
    0.44
    te
    0.43
    issa
    0.43
     全
    0.43
    ats
    0.43
    ↵
    0.43
     tots
    0.42
    Activations Density 0.000%

    No Known Activations