© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 114263
    Prev
    Next
    INDEX
    Explanations

    following "front", "member", "worship", "help"

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

    explicit 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
    inks
    0.48
    ६
    0.47
     laver
    0.46
    т
    0.45
     r
    0.44
    м
    0.44
     d
    0.43
    複雜
    0.42
     wash
    0.42
     nt
    0.42
    POSITIVE LOGITS
     franchisees
    0.50
    性感
    0.48
     なかっ
    0.45
    verts
    0.44
     expon
    0.43
     irresistible
    0.43
     八
    0.43
     胸
    0.42
     harmonique
    0.42
    alev
    0.42
    Activations Density 0.000%

    No Known Activations