© 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. 150731
    Prev
    Next
    INDEX
    Explanations

    concentrations of control

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

    start small or gradually

    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
    IG
    0.47
    RY
    0.46
    Roberts
    0.45
     ক্রমাগত
    0.45
    Im
    0.44
    benz
    0.44
     Roberts
    0.44
    b
    0.44
     Lange
    0.43
    Inactive
    0.43
    POSITIVE LOGITS
     symplect
    0.52
     questionnaires
    0.51
     usernames
    0.50
    ॉज
    0.50
     eateries
    0.49
     tinc
    0.49
     bibliographic
    0.49
     reconstructions
    0.48
    णू
    0.48
     middlewares
    0.47
    Activations Density 0.000%

    No Known Activations