© 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. 219305
    Prev
    Next
    INDEX
    Explanations

    begin various activities

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

    filing cabinet, Newton, table, search

    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
    вед
    0.50
     технология
    0.48
    یر
    0.47
    гада
    0.43
    ที่เรา
    0.42
     و
    0.42
    стрее
    0.42
    пера
    0.41
    шен
    0.41
    햐
    0.41
    POSITIVE LOGITS
     肩
    0.52
     棚
    0.52
     সংযুক্ত
    0.48
    university
    0.48
    teenth
    0.47
     初期
    0.47
     大阪
    0.47
    %;
    0.46
    TOP
    0.45
    etto
    0.44
    Activations Density 0.006%

    No Known Activations