© 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. 152600
    Prev
    Next
    INDEX
    Explanations

    receive your password

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

    head over, resolution and, those children, stringy thingy

    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
    НИЕ
    0.46
    淖
    0.46
    IMENTS
    0.45
     лаборатор
    0.44
     банк
    0.44
     geochemistry
    0.44
    \
    0.44
    :
    0.44
     Autón
    0.43
    厝
    0.42
    POSITIVE LOGITS
     সত্যা
    0.52
     zwięks
    0.48
    龈
    0.47
    increase
    0.46
     আঙ্গ
    0.45
    Lyric
    0.45
     حقیقت
    0.44
     αι
    0.44
     sinistra
    0.43
     zmniejs
    0.43
    Activations Density 0.001%

    No Known Activations