© 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. 148050
    Prev
    Next
    INDEX
    Explanations

    requirements

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

    database, time, change, arguments

    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
    =>
    0.46
     البر
    0.46
    ayakan
    0.46
    liver
    0.45
    vl
    0.43
    ıyordu
    0.43
    weig
    0.43
    yczne
    0.43
    으며
    0.43
     अच्छ
    0.42
    POSITIVE LOGITS
     ulic
    0.46
    誰も
    0.46
    做
    0.45
     checkIf
    0.44
    羅
    0.44
    わかる
    0.43
     useSelector
    0.43
     DATABASE
    0.43
    化学
    0.43
     hustle
    0.43
    Activations Density 0.001%

    No Known Activations