© 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. 244139
    Prev
    Next
    INDEX
    Explanations

    self or good thing

    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
    闿
    0.49
    maxim
    0.48
    先に
    0.48
     প্রথমেই
    0.47
    ereo
    0.46
    টাইমস
    0.46
    聶
    0.45
    ੀ
    0.44
    🐦
    0.44
    DOMContentLoaded
    0.44
    POSITIVE LOGITS
     unspoken
    0.52
     бути
    0.50
     trekking
    0.49
     marshmallows
    0.49
     backcountry
    0.49
    )//
    0.49
     ”
    0.48
     shock
    0.48
     leggings
    0.48
     trophies
    0.48
    Activations Density 0.001%

    No Known Activations