© 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. 181634
    Prev
    Next
    INDEX
    Explanations

    stand or play

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

    highlighting subtle undercurrents

    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
    ҳо
    0.50
    ী
    0.47
     تاریخی
    0.47
    త్‌
    0.46
    ренные
    0.46
    omethane
    0.46
     привіт
    0.45
    時の
    0.43
    </em>
    0.43
     Flow
    0.43
    POSITIVE LOGITS
     bicicletas
    0.50
     dupla
    0.47
     interrom
    0.45
     ماما
    0.45
     suma
    0.45
    以为
    0.44
     laissant
    0.44
    的两
    0.43
    要在
    0.43
    在一
    0.42
    Activations Density 0.001%

    No Known Activations