© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12584
    Prev
    Next
    INDEX
    Explanations

    product variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     możliwość
    0.45
    ེད་
    0.43
     SESSION
    0.43
     SUBS
    0.42
     voie
    0.41
     DUT
    0.41
     harmful
    0.41
     엔
    0.41
     aplicación
    0.41
     SNR
    0.41
    POSITIVE LOGITS
    та
    0.45
    ль
    0.43
    য়ের
    0.42
    ю
    0.41
    ngen
    0.40
    hashed
    0.40
    のデザイン
    0.40
    в
    0.39
    ш
    0.38
    γου
    0.37
    Activations Density 0.000%

    No Known Activations