© 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. 122103
    Prev
    Next
    INDEX
    Explanations

    United States, daily cleaning, announced by

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

    for communication, demanded we, release/*

    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
     spekt
    0.52
    പര
    0.51
    加工
    0.50
    കെ
    0.50
    ล
    0.49
    bending
    0.49
    പൊ
    0.46
    มา
    0.46
     ഹോളി
    0.46
    ܠ
    0.46
    POSITIVE LOGITS
    сів
    0.45
    os
    0.43
     VIP
    0.43
     filter
    0.43
     wikiHow
    0.42
     существует
    0.42
     blancos
    0.42
     crónica
    0.42
     Ж
    0.41
     funcionarios
    0.41
    Activations Density 0.001%

    No Known Activations