© 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. 46827
    Prev
    Next
    INDEX
    Explanations

    neuroscientist, CD, schedule, MEs, auto, behind, question

    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
     animations
    0.44
    ніза
    0.42
     pulsations
    0.41
    +{\
    0.41
     frå
    0.41
     STATION
    0.40
    夊
    0.40
    <unused76>
    0.40
     synerg
    0.40
     UAS
    0.39
    POSITIVE LOGITS
     তল
    0.48
     Екатери
    0.48
    res
    0.46
    ice
    0.46
    ample
    0.46
    지
    0.45
    sec
    0.44
    YO
    0.43
    ct
    0.43
    <0x0D>
    0.42
    Activations Density 0.001%

    No Known Activations