© 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. 62194
    Prev
    Next
    INDEX
    Explanations

    stamp, CA, trend, attached

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

    defining concepts and their subsequent descriptions

    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
     standardization
    0.44
    beds
    0.43
    models
    0.42
    ead
    0.41
    o
    0.41
     globale
    0.41
     mechanism
    0.39
    verify
    0.39
    Lind
    0.39
     mechanisms
    0.39
    POSITIVE LOGITS
     miesią
    0.54
     이벤트
    0.54
    тива
    0.52
    蒨
    0.50
     прошлом
    0.48
    ênd
    0.48
    urta
    0.48
     Kih
    0.48
    썸
    0.47
     Bayern
    0.46
    Activations Density 0.000%

    No Known Activations