© 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. 40-GEMMASCOPE-2-RES-65K
    7. 47410
    Prev
    Next
    INDEX
    Explanations

    adding new things without changing

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ArrayAdapter
    0.45
    VCTargetsPath
    0.42
    梵
    0.41
     watersheds
    0.40
    getCameraId
    0.39
    tFileInputExcel
    0.38
     coltiv
    0.38
    <unused2140>
    0.38
     sagittal
    0.38
     glab
    0.37
    POSITIVE LOGITS
     Time
    0.42
     L
    0.41
     Asking
    0.41
    Rounding
    0.41
    Asking
    0.40
     Making
    0.39
    D
    0.39
    L
    0.39
    Six
    0.38
     बाट
    0.38
    Activations Density 0.000%

    No Known Activations