© 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. 142925
    Prev
    Next
    INDEX
    Explanations

    with... a/the/number/description

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

    con + article/noun

    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
    一
    0.60
    ኵ
    0.52
     מפ
    0.49
    联
    0.47
    架构
    0.46
     одном
    0.46
    一看
    0.46
    科
    0.45
     εφαρ
    0.45
    一部分
    0.44
    POSITIVE LOGITS
     impunity
    0.57
     demikian
    0.53
     gusto
    0.50
     respect
    0.47
     far
    0.46
     shortcut
    0.45
     respeto
    0.45
     разными
    0.44
    god
    0.44
    gel
    0.43
    Activations Density 0.065%

    No Known Activations