© 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-262K
    7. 192223
    Prev
    Next
    INDEX
    Explanations

    spending price <0xC2>

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     eyelashes
    0.41
     affluent
    0.39
     hydraulic
    0.38
     ilmiah
    0.38
    ーフ
    0.37
     Hydraulic
    0.37
     eyelash
    0.37
     mile
    0.37
     gulf
    0.37
    秫
    0.37
    POSITIVE LOGITS
    more
    0.40
    subdirectory
    0.38
    struct
    0.38
     structs
    0.38
    CreateCharacter
    0.37
     والخ
    0.37
    ľ
    0.37
    att
    0.36
    一個
    0.36
    使其
    0.36
    Activations Density 0.000%

    No Known Activations