© 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. 2794
    Prev
    Next
    INDEX
    Explanations

    go code imports

    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
    Not in Any Lists

    No Comments

    Negative Logits
    焲
    0.42
     pyrid
    0.39
    饞
    0.38
     chemically
    0.38
     Lipid
    0.38
    rugada
    0.38
     wrinkled
    0.37
    綃
    0.37
    <unused27>
    0.36
    ruits
    0.36
    POSITIVE LOGITS
    github
    0.87
    fmt
    0.87
     github
    0.84
     fmt
    0.79
    testing
    0.65
    encoding
    0.65
     GitHub
    0.65
    time
    0.61
     Github
    0.61
     strconv
    0.60
    Activations Density 0.005%

    No Known Activations