© 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. 144939
    Prev
    Next
    INDEX
    Explanations

    very supportive

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

    system commands and structures

    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
    가
    0.47
    від
    0.44
     pousser
    0.44
    أس
    0.44
    边
    0.44
    那
    0.44
    akal
    0.43
    が
    0.43
    ä
    0.42
     that
    0.42
    POSITIVE LOGITS
    gtk
    0.58
    シャレ
    0.54
    ativen
    0.52
    matchCondition
    0.51
    ستي
    0.50
     Studenten
    0.48
     Цуки
    0.48
    嵐
    0.47
     Noeud
    0.47
     வாய
    0.47
    Activations Density 0.000%

    No Known Activations