© 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. 79615
    Prev
    Next
    INDEX
    Explanations

    downloading and printing

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

    specific skills, industry, journal

    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
    चिंत
    0.50
    ைய
    0.48
     minded
    0.45
    ныгы
    0.45
    лий
    0.44
    mán
    0.44
    нє
    0.43
    í
    0.43
    ственно
    0.43
    intended
    0.43
    POSITIVE LOGITS
     النقطه
    0.47
    Moon
    0.45
     కొత్త
    0.43
     የመጀመሪያ
    0.42
     شف
    0.42
     رکھا
    0.42
     vVertex
    0.42
     وہی
    0.41
    টারের
    0.41
     অঞ্চ
    0.40
    Activations Density 0.001%

    No Known Activations