© 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. 12897
    Prev
    Next
    INDEX
    Explanations

    configuration and code structures

    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
     intimate
    0.43
     Schwarzschild
    0.43
    劧
    0.39
     menacing
    0.39
     هنگام
    0.38
     Miami
    0.38
     Castillo
    0.37
    small
    0.37
     meant
    0.37
    approximately
    0.36
    POSITIVE LOGITS
    顶点
    0.41
    皱
    0.39
    KIN
    0.38
    温泉
    0.38
    ICES
    0.37
    ojen
    0.37
     LINK
    0.36
    oj
    0.36
     અધ
    0.36
    ச்சிக்க
    0.36
    Activations Density 0.000%

    No Known Activations