© 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. 47348
    Prev
    Next
    INDEX
    Explanations

    Gradle build and task commands

    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
    )](
    0.42
    帐户
    0.41
     次元
    0.40
     Dancer
    0.38
    開発
    0.38
    KBr
    0.37
    Scatter
    0.37
    ADOR
    0.37
     matroid
    0.36
    Denominator
    0.36
    POSITIVE LOGITS
     './
    0.47
     clean
    0.46
    construct
    0.44
     "./
    0.43
     assemble
    0.42
    ('./
    0.42
     classes
    0.42
     '-
    0.41
     validate
    0.41
     task
    0.41
    Activations Density 0.008%

    No Known Activations