© 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. 59755
    Prev
    Next
    INDEX
    Explanations

    launch, map, split, school, parameter

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

    coworkers message

    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
     adım
    0.48
    djang
    0.48
    startGame
    0.48
    startsWith
    0.47
    ｌ
    0.46
     berjudul
    0.46
     kadın
    0.45
    ną
    0.45
    woł
    0.45
     restoran
    0.43
    POSITIVE LOGITS
     מב
    0.49
     confronted
    0.47
     shafts
    0.45
     follicles
    0.45
     Fiberglass
    0.45
     parses
    0.44
     ترى
    0.44
     gums
    0.44
    琺
    0.44
     stabilizers
    0.43
    Activations Density 0.000%

    No Known Activations