© 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. 44826
    Prev
    Next
    INDEX
    Explanations

    secret, candidates, or laurels

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

    arguments passed when

    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
    id
    0.62
    ки
    0.50
    ika
    0.50
     T
    0.49
     Daftar
    0.49
     G
    0.48
    P
    0.48
     Pentagon
    0.48
     MENU
    0.47
    idla
    0.47
    POSITIVE LOGITS
    ருக்கு
    0.49
     അഭി
    0.47
     precisamente
    0.45
     punctured
    0.44
     punched
    0.44
     fertilized
    0.44
    ването
    0.43
    infer
    0.42
    Swiss
    0.42
    -{\
    0.42
    Activations Density 0.001%

    No Known Activations