© 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. 17925
    Prev
    Next
    INDEX
    Explanations

    code commands and programming constructs

    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
     Faced
    0.39
     P
    0.39
     faced
    0.39
    faced
    0.39
     Face
    0.38
     Mặt
    0.38
    พิมพ์
    0.37
    5
    0.36
    face
    0.36
    R
    0.36
    POSITIVE LOGITS
     EventEmitter
    0.46
     தலைநக
    0.45
    middlewares
    0.44
     ప్రయత్
    0.43
    ोसिएशन
    0.42
     গুলির
    0.42
     এরই
    0.41
    loadNpm
    0.41
    OpportunitiesBy
    0.40
     或
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.