© 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. 225224
    Prev
    Next
    INDEX
    Explanations

    passed through various

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

    concepts and contexts

    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
    платно
    0.51
    strategy
    0.47
    bookmarks
    0.47
     बताता
    0.46
    >((
    0.45
    danger
    0.45
    ALTH
    0.44
    heiten
    0.44
    новая
    0.44
    }[(
    0.44
    POSITIVE LOGITS
     futbol
    0.49
     waar
    0.49
     Apache
    0.49
     viss
    0.49
     Saddam
    0.46
     Jaguars
    0.46
     establecer
    0.45
     abraz
    0.45
     Tener
    0.44
     promove
    0.44
    Activations Density 0.000%

    No Known Activations