© 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. 97130
    Prev
    Next
    INDEX
    Explanations

    eyebrow pencils, expected in, PBIS

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

    sales order, pixels, acquisition of, Dios

    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
    AM
    0.52
    ingresso
    0.51
    because
    0.50
    odon
    0.48
    YW
    0.48
    ย
    0.47
    id
    0.46
    ިން
    0.45
    سٹم
    0.45
    invocation
    0.45
    POSITIVE LOGITS
    ్రే
    0.45
    빔
    0.45
    㭐
    0.45
    qi
    0.45
    浆
    0.45
     Finite
    0.44
    镗
    0.44
    <0xE2>
    0.43
     дело
    0.42
     নূর
    0.42
    Activations Density 0.001%

    No Known Activations