© 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. 249339
    Prev
    Next
    INDEX
    Explanations

    well-being and goals

    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
    肴
    0.48
    ८
    0.46
    சின
    0.45
    《
    0.44
    レア
    0.43
    ાઇ
    0.43
    拉丁
    0.43
    凄
    0.43
    пов
    0.43
    вано
    0.43
    POSITIVE LOGITS
     arty
    0.49
     park
    0.45
    stopper
    0.45
     Amnesty
    0.45
     Marijuana
    0.45
     urinary
    0.44
     MDA
    0.44
     Bikini
    0.44
    巉
    0.44
     pants
    0.44
    Activations Density 0.001%

    No Known Activations