© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3826
    Prev
    Next
    INDEX
    Explanations

    which introduces definitions

    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_31_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
    യോ
    0.42
    ansas
    0.42
    ведений
    0.42
     новий
    0.41
     ژوند
    0.41
     黒
    0.40
    iony
    0.40
    RAMM
    0.39
     letech
    0.39
    তরাং
    0.39
    POSITIVE LOGITS
    是
    0.47
     isn
    0.45
    Nest
    0.44
    不是
    0.43
    定义
    0.43
     translates
    0.41
    叫做
    0.41
     abbreviation
    0.40
    សម
    0.40
    分为
    0.39
    Activations Density 0.002%

    No Known Activations