© 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. 101168
    Prev
    Next
    INDEX
    Explanations

    Item 1.2; Item 22

    np_acts-logits-general · gemini-2.5-flash-lite

    parenthetical punctuation and keywords

    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
     سامان
    0.55
    呥
    0.51
    茟
    0.50
     Globalization
    0.48
     Crawley
    0.48
     Tân
    0.47
     Ester
    0.46
    䣵
    0.46
    🧍
    0.46
    媧
    0.46
    POSITIVE LOGITS
    uk
    0.60
    ;
    0.58
    =
    0.55
    ?
    0.55
    ig
    0.50
    hub
    0.47
    up
    0.47
    :
    0.46
    ang
    0.46
    ww
    0.46
    Activations Density 0.001%

    No Known Activations