© 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. 97847
    Prev
    Next
    INDEX
    Explanations

    prior tax, last points, GATE score, Street offices

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

    explaining preparation or reasoning

    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
     fonctionnement
    0.53
     funcionamento
    0.52
    ندوق
    0.51
     Royaume
    0.45
     finishing
    0.45
     apparence
    0.43
    ဢ
    0.43
     zapewn
    0.43
    "
    0.41
    ቤ
    0.41
    POSITIVE LOGITS
    ಕಿ
    0.54
     summar
    0.51
     gerne
    0.51
    ීමේ
    0.49
    kHz
    0.47
    पुरा
    0.46
     الجز
    0.46
     रूपए
    0.46
    pline
    0.45
    abilia
    0.45
    Activations Density 0.001%

    No Known Activations