© 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. 56070
    Prev
    Next
    INDEX
    Explanations

    stuff

    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
    Not in Any Lists

    No Comments

    Negative Logits
    妃
    0.47
     Possible
    0.42
    OR
    0.39
    俐
    0.39
     Curious
    0.39
    мпа
    0.38
     curious
    0.38
     perceived
    0.38
    ktor
    0.38
    寂
    0.38
    POSITIVE LOGITS
    Stuff
    0.62
     stuff
    0.61
     Stuff
    0.58
    stuff
    0.54
     stuffing
    0.54
     relleno
    0.52
     stuffs
    0.50
     fillers
    0.44
     Wolver
    0.43
     স্টাফ
    0.43
    Activations Density 0.006%

    No Known Activations