© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21846
    Prev
    Next
    INDEX
    Explanations

    cat's whiskers and fur

    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
    Negative Logits
     physicochemical
    0.41
    ༘
    0.39
    物体
    0.39
    คุณ
    0.38
    Neut
    0.37
     Newtonian
    0.37
    奉
    0.37
    ซ์
    0.37
    Regression
    0.37
     cosmos
    0.37
    POSITIVE LOGITS
    <unused2148>
    0.42
     εται
    0.41
     confidential
    0.38
     помогает
    0.38
     банков
    0.37
    ∙
    0.37
     rum
    0.36
    商标
    0.36
     مالی
    0.36
     banking
    0.35
    Activations Density 0.002%

    No Known Activations