© 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. 31-GEMMASCOPE-2-RES-65K
    7. 54523
    Prev
    Next
    INDEX
    Explanations

    same asset, region, project, row, package, action, object

    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_65k_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
    ’
    0.52
    similar
    0.46
    ileg
    0.46
     enumerate
    0.45
     enviable
    0.45
    ്
    0.44
    similarity
    0.44
     identique
    0.44
     Srbiji
    0.44
    <h4>
    0.43
    POSITIVE LOGITS
     selben
    0.70
     same
    0.62
     같은
    0.58
     stesso
    0.57
     mismo
    0.56
     samym
    0.54
     cerveau
    0.53
     aynı
    0.50
     as
    0.49
     muziek
    0.49
    Activations Density 0.043%

    No Known Activations