© 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. 16-GEMMASCOPE-2-RES-262K
    7. 144579
    Prev
    Next
    INDEX
    Explanations

    ALGORITHM = value

    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
    ǚ
    0.50
     jumps
    0.48
    yue
    0.48
     figurine
    0.46
    InitTypeDef
    0.45
    alysis
    0.45
     күзгү
    0.44
    かけ
    0.44
    ய்ப்ப
    0.44
    chuk
    0.43
    POSITIVE LOGITS
    ده
    0.59
     educa
    0.54
    یا
    0.53
    ের
    0.52
    িক
    0.50
    )$,
    0.50
    ئ
    0.49
     kemudian
    0.47
     dahulu
    0.47
     automobiles
    0.47
    Activations Density 0.000%

    No Known Activations