© 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. 18439
    Prev
    Next
    INDEX
    Explanations

    time markers

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

    mid or after

    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
     Ready
    0.43
    spaceBetween
    0.43
    睽
    0.42
     Applicable
    0.40
     Kochi
    0.40
    श्यक
    0.39
     नरेंद्र
    0.39
    🆚
    0.39
     Tarifleri
    0.39
    ursos
    0.38
    POSITIVE LOGITS
     midway
    0.93
     halfway
    0.91
    途中
    0.72
     midpoint
    0.71
     shortly
    0.68
    途
    0.68
     before
    0.58
     Midway
    0.58
    Shortly
    0.53
     prematurely
    0.53
    Activations Density 0.112%

    No Known Activations