© 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. 135718
    Prev
    Next
    INDEX
    Explanations

    credit, Liquid, handy, So, for, One, doing

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

    pandemics

    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
    रक
    0.47
    ዢ
    0.46
    Universität
    0.46
    戙
    0.46
    மதி
    0.45
    rowIndex
    0.44
    метров
    0.43
     زائدا
    0.43
    瘾
    0.43
    ρκ
    0.43
    POSITIVE LOGITS
     スリム
    0.50
     IV
    0.48
     cuatro
    0.46
    );
    0.45
    asi
    0.45
     cantidades
    0.45
     varias
    0.45
     교
    0.44
     cuento
    0.44
     आपसी
    0.44
    Activations Density 0.001%

    No Known Activations