© 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. 91123
    Prev
    Next
    INDEX
    Explanations

    columns and arrays

    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
    ବା
    0.50
    酘
    0.50
    త్రిక
    0.47
    াদক
    0.47
    椑
    0.47
    น
    0.46
    न
    0.46
     क्रिप्टोकरेंसी
    0.46
    钚
    0.46
    नंतर
    0.45
    POSITIVE LOGITS
    aged
    0.47
     recognises
    0.46
    prised
    0.45
    parameters
    0.45
     dáng
    0.45
    recogn
    0.44
     bodily
    0.44
     verifies
    0.44
    pressed
    0.43
     ラック
    0.43
    Activations Density 0.001%

    No Known Activations