© 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. 13609
    Prev
    Next
    INDEX
    Explanations

    years and everyday life

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

    lists, selectors, or properties

    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
    を提供
    0.49
     Barrios
    0.47
     Mois
    0.46
    <<
    0.45
     Aro
    0.44
     Buss
    0.44
     Lant
    0.43
     Barrel
    0.43
     steered
    0.42
    ীশ
    0.41
    POSITIVE LOGITS
     perfettamente
    0.48
     तत्काल
    0.46
     비슷한
    0.46
    খণ্ড
    0.44
     রোববার
    0.43
     ე
    0.43
    hdu
    0.43
     justo
    0.42
    watering
    0.42
     អ្នក
    0.42
    Activations Density 0.001%

    No Known Activations