© 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. 28209
    Prev
    Next
    INDEX
    Explanations

    terminology used

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

    Python package installer

    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
     प्रमेय
    0.48
     ଭ
    0.47
     xổ
    0.45
     ဖ
    0.44
    holiday
    0.43
    ភ្ល
    0.43
     المالية
    0.43
     উপহার
    0.42
     دھو
    0.42
     তা
    0.41
    POSITIVE LOGITS
    РИ
    0.53
    шие
    0.44
    веден
    0.43
    აქ
    0.42
     Hab
    0.42
     Starts
    0.42
     früheren
    0.41
    ✋
    0.41
    ிக
    0.40
    ாவின்
    0.40
    Activations Density 0.000%

    No Known Activations