© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11173
    Prev
    Next
    INDEX
    Explanations

    curling eyelashes

    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_40_width_16k_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
    𒂵
    0.45
    squa
    0.42
     polycarbonate
    0.41
    逈
    0.41
     ово
    0.41
    <unused40>
    0.41
    बीर
    0.39
    voices
    0.39
    ổ
    0.39
     tokens
    0.38
    POSITIVE LOGITS
     curl
    1.21
     curling
    1.16
    curl
    1.05
    Curl
    1.05
     curled
    1.02
     Curl
    1.01
     curls
    1.00
     Curling
    0.98
     lash
    0.95
     eyelid
    0.93
    Activations Density 0.088%

    No Known Activations