© 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. 237986
    Prev
    Next
    INDEX
    Explanations

    Kevlar

    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
     carbonates
    0.58
    ServiceGroupID
    0.52
     launchers
    0.49
    ون
    0.49
    캅
    0.48
    윰
    0.48
     contenders
    0.48
     currants
    0.48
    براير
    0.47
     médicaments
    0.47
    POSITIVE LOGITS
    Movie
    0.52
     States
    0.50
     By
    0.49
     Revised
    0.49
     Movie
    0.48
     '
    0.48
     Based
    0.47
     Through
    0.46
     Procedure
    0.46
     Feeling
    0.46
    Activations Density 0.000%

    No Known Activations