© 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. 246584
    Prev
    Next
    INDEX
    Explanations

    questions, any, or both

    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
    )$
    0.52
     majesty
    0.48
    )$.
    0.43
    ടിച്ച
    0.41
    幸せ
    0.40
     offens
    0.40
    カタログ
    0.40
     CHARSET
    0.40
    瞻
    0.40
    心の
    0.40
    POSITIVE LOGITS
    ьера
    0.55
     వ్య
    0.53
    ueel
    0.52
    usser
    0.52
    ЛА
    0.51
    elina
    0.50
    atzen
    0.49
     geschaffen
    0.48
    لين
    0.48
    Mve
    0.48
    Activations Density 0.000%

    No Known Activations