© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178658
    Prev
    Next
    INDEX
    Explanations

    information available

    np_acts-logits-general · gemini-2.5-flash-lite

    breakdown of factors and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awah
    0.46
     I
    0.44
    注解
    0.44
    ola
    0.41
    当作
    0.41
    odat
    0.41
     patrol
    0.40
    ¨
    0.40
    只有一个
    0.40
     Clin
    0.40
    POSITIVE LOGITS
    ulière
    0.56
    Serbia
    0.53
    Nutrition
    0.49
    Five
    0.48
    extré
    0.47
    Href
    0.47
     setTheme
    0.46
    StillWater
    0.46
    Routine
    0.46
    Olivia
    0.46
    Activations Density 0.001%

    No Known Activations