© 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. 232096
    Prev
    Next
    INDEX
    Explanations

    monochrome patterned

    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
     autonomía
    0.49
     ဟ
    0.48
    ädt
    0.47
    ívá
    0.47
     auteurs
    0.45
     подчи
    0.44
     সরাস
    0.44
     акты
    0.44
    Autonomous
    0.44
     کھول
    0.43
    POSITIVE LOGITS
     aż
    0.47
    ᆹ
    0.45
    ܫ
    0.44
    bris
    0.44
    icionar
    0.44
    複雜
    0.44
     kiln
    0.43
     $+
    0.43
    weza
    0.43
     diamante
    0.43
    Activations Density 0.000%

    No Known Activations