© 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. 248183
    Prev
    Next
    INDEX
    Explanations

    health, call, connected, strengthen

    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
    شي
    0.50
    ing
    0.49
    fledged
    0.45
     donate
    0.44
    -
    0.40
     Monsanto
    0.40
     -
    0.40
    ти
    0.40
    าว
    0.39
     prett
    0.39
    POSITIVE LOGITS
     맥
    0.61
     فرهنگ
    0.52
     პირადი
    0.52
     문화
    0.50
    Turning
    0.50
     మరియు
    0.49
     রাগ
    0.49
    徠
    0.49
     빛
    0.49
     مذہب
    0.49
    Activations Density 0.001%

    No Known Activations