© 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. 38252
    Prev
    Next
    INDEX
    Explanations

    creating space, defining, scoring transactions

    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
    ısının
    0.55
    舷
    0.48
     препят
    0.47
     ஏற
    0.47
     пе
    0.46
    ผ่าน
    0.46
    分岐
    0.46
    髌
    0.45
    이며
    0.45
    晛
    0.44
    POSITIVE LOGITS
     schnelle
    0.50
     jedes
    0.46
     naira
    0.46
     fandom
    0.45
     jede
    0.45
    coord
    0.44
     szko
    0.44
     dinero
    0.44
     rojos
    0.43
    াল
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.