© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135925
    Prev
    Next
    INDEX
    Explanations

    attachment operation

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

    possibility, files, index

    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
     F
    0.48
     trên
    0.47
    斌
    0.47
                          
    0.46
     H
    0.44
    ez
    0.43
     Thương
    0.43
     選
    0.43
     chiếc
    0.43
    các
    0.43
    POSITIVE LOGITS
     contexts
    0.50
     harmless
    0.49
     democracies
    0.47
     innocuous
    0.47
     mildly
    0.47
     ومد
    0.46
     benign
    0.45
     accidens
    0.45
     somewhat
    0.45
     eminently
    0.44
    Activations Density 0.001%

    No Known Activations