© 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. 143191
    Prev
    Next
    INDEX
    Explanations

    behavior therapy, officially announces, odds of

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

    religious tenets

    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
    abolic
    0.50
     Hartmann
    0.46
     Kirkpatrick
    0.46
     plus
    0.45
     Bundestag
    0.44
    intensive
    0.44
     Kit
    0.44
    ️
    0.44
     Intensive
    0.43
     Weib
    0.43
    POSITIVE LOGITS
     කර
    0.46
    धिक
    0.46
     रिए
    0.46
     accès
    0.45
    データを
    0.45
     acceso
    0.44
    ަތ
    0.43
     thrived
    0.43
     realidade
    0.43
    データの
    0.42
    Activations Density 0.001%

    No Known Activations