© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27524
    Prev
    Next
    INDEX
    Explanations

    python code constructs

    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
    jButton
    0.54
     numOf
    0.49
     ////
    0.46
     jButton
    0.46
    distanceArray
    0.45
    numOf
    0.45
    centerX
    0.45
    ));//
    0.45
     JButton
    0.44
     jTextField
    0.44
    POSITIVE LOGITS
     isinstance
    0.75
    ._
    0.73
     iterable
    0.71
     _
    0.70
    StringIO
    0.68
     hasattr
    0.68
    kwargs
    0.66
     pytest
    0.65
     getattr
    0.64
    iterable
    0.64
    Activations Density 0.006%

    No Known Activations