© 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. 23850
    Prev
    Next
    INDEX
    Explanations

    highest standards or circuit

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

    steps and options

    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
    $
    0.46
     scrotum
    0.45
    qt
    0.45
    zh
    0.45
     impair
    0.45
    bh
    0.44
     legitimately
    0.43
     corroborate
    0.43
    gette
    0.43
     ,
    0.42
    POSITIVE LOGITS
     sveik
    0.49
     BALANCE
    0.48
     ThemeOverlay
    0.47
    ปก
    0.46
    輥
    0.46
     பகி
    0.46
    Fireworks
    0.46
    Рас
    0.45
    მი
    0.45
    間の
    0.45
    Activations Density 0.000%

    No Known Activations