© 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. 70974
    Prev
    Next
    INDEX
    Explanations

    rescuing and protecting

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

    two copies pattern

    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
    Negative Logits
    Drama
    0.47
    AST
    0.44
    ordinating
    0.44
    únior
    0.43
    丝毫
    0.43
    ╔
    0.43
     காற்றின்
    0.42
     स्टूडियो
    0.42
    Stores
    0.41
    Wend
    0.41
    POSITIVE LOGITS
     toto
    0.50
     concealment
    0.50
    ُل
    0.49
     organes
    0.48
     organe
    0.48
     organ
    0.48
    年から
    0.48
     euthanasia
    0.47
     უფრო
    0.46
    ファスナー
    0.45
    Activations Density 0.001%

    No Known Activations