© 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. 81756
    Prev
    Next
    INDEX
    Explanations

    4. notation

    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
     uts
    0.46
     schnell
    0.46
     interessant
    0.46
     repairing
    0.41
    ittal
    0.41
    $-,
    0.41
    ద్య
    0.41
     sisält
    0.40
    불
    0.40
     ruling
    0.39
    POSITIVE LOGITS
     CCSDT
    0.54
     fibrils
    0.49
     кален
    0.48
    IKA
    0.48
     BEGIN
    0.46
     Петер
    0.46
    Cette
    0.46
    Ibid
    0.46
    BST
    0.46
    Etudes
    0.46
    Activations Density 0.001%

    No Known Activations