© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 116149
    Prev
    Next
    INDEX
    Explanations

    first Harry Potter

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

    sovereignty, claims, and data

    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
     Рас
    0.53
    එ
    0.49
    jší
    0.46
     doloribus
    0.45
    phar
    0.44
     Shelby
    0.44
    гії
    0.44
     архівів
    0.43
     strut
    0.43
    %%%%%%%%%%%%%%%%
    0.43
    POSITIVE LOGITS
    }(
    0.45
    colour
    0.43
    ול
    0.42
    itochond
    0.42
     અનુ
    0.42
    also
    0.41
    residuals
    0.41
     negócios
    0.40
     ganó
    0.40
    traffic
    0.40
    Activations Density 0.000%

    No Known Activations