© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 118096
    Prev
    Next
    INDEX
    Explanations

    acculab plc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    の
    0.90
    의
    0.84
    ב
    0.77
    は
    0.75
    감
    0.74
    ^{\
    0.73
    માં
    0.73
    는
    0.72
     Zas
    0.72
    ט
    0.72
    POSITIVE LOGITS
    ja
    0.75
    p
    0.71
    os
    0.69
    t
    0.68
    <unused1763>
    0.62
    ba
    0.61
    ton
    0.59
    ارات
    0.59
     клі
    0.59
     किंग्स
    0.58
    Activations Density 0.000%

    No Known Activations