© 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. 17974
    Prev
    Next
    INDEX
    Explanations

    ofafter

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

    components and economy

    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
    ка
    0.55
    ﮐ
    0.51
    ин
    0.49
    لز
    0.47
    кон
    0.46
    ان
    0.46
    по
    0.44
    ена
    0.44
    PROPERTY
    0.43
    ร
    0.43
    POSITIVE LOGITS
     imaged
    0.46
     embell
    0.46
     axonal
    0.46
     fortement
    0.45
    తులను
    0.45
     μιας
    0.44
     atlet
    0.43
     laterales
    0.43
     erred
    0.43
     adept
    0.42
    Activations Density 0.000%

    No Known Activations