© 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. 251486
    Prev
    Next
    INDEX
    Explanations

    regulations and restrictions

    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
     φι
    0.57
     фи
    0.52
     hém
    0.51
     ради
    0.49
     мани
    0.49
     коллек
    0.48
    濋
    0.48
     টা
    0.47
    hém
    0.47
     الدا
    0.46
    POSITIVE LOGITS
     mathematically
    0.47
     arre
    0.46
     presupp
    0.46
    Ã
    0.45
     ascertained
    0.45
    Â
    0.45
    否
    0.44
     grava
    0.44
     incompre
    0.43
    نی
    0.42
    Activations Density 0.001%

    No Known Activations