© 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. 152871
    Prev
    Next
    INDEX
    Explanations

    January 31

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

    describing state or context

    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
    hor
    0.45
     haem
    0.44
     chill
    0.43
    idega
    0.43
     wasn
    0.43
     nasceu
    0.43
     laget
    0.42
     n
    0.42
     odds
    0.42
     Samsung
    0.41
    POSITIVE LOGITS
    balances
    0.53
    timestamps
    0.51
     reverts
    0.49
    Tovar
    0.48
    룔
    0.47
     ಪ್ರಾರಂಭ
    0.47
     модер
    0.45
    馭
    0.45
     बह
    0.44
    providecommand
    0.44
    Activations Density 0.001%

    No Known Activations