© 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. 72366
    Prev
    Next
    INDEX
    Explanations

    activities and durations

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

    keeps trying

    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
     Angelo
    0.50
    ліся
    0.47
    την
    0.43
     Fortuna
    0.43
    <0xAF>
    0.42
    وران
    0.42
    λώ
    0.42
    ppins
    0.42
     acides
    0.42
     Merchants
    0.41
    POSITIVE LOGITS
    achelor
    0.53
     vendo
    0.51
     👍
    0.48
     uses
    0.48
     usos
    0.47
     nadal
    0.46
     veo
    0.46
     dir
    0.46
     violates
    0.46
     frust
    0.46
    Activations Density 0.000%

    No Known Activations