© 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. 177157
    Prev
    Next
    INDEX
    Explanations

    academic and educational terms

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

    breakdowns or lists

    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
    われている
    0.59
    ология
    0.54
    مركز
    0.52
    اك
    0.48
    漲
    0.48
    ویت
    0.47
    وما
    0.47
     অঞ্চলের
    0.46
    を中心
    0.46
     odnosno
    0.46
    POSITIVE LOGITS
     aphids
    0.52
    ?\
    0.51
     you
    0.50
     lcd
    0.48
     jigs
    0.48
    ?
    0.47
     ergonom
    0.46
     calcium
    0.46
    ?..
    0.46
    inté
    0.45
    Activations Density 0.000%

    No Known Activations