© 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. 216753
    Prev
    Next
    INDEX
    Explanations

    lists of options or categories

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

    做出选择

    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
     lézards
    0.67
     вещества
    0.57
     tortues
    0.57
     postérieures
    0.55
    󰡔
    0.55
     crianças
    0.54
     którzy
    0.54
     fermeture
    0.54
     площади
    0.54
     اكو
    0.54
    POSITIVE LOGITS
    ID
    0.52
    State
    0.52
    ta
    0.51
    Session
    0.50
    i
    0.50
    P
    0.48
    Type
    0.48
    (
    0.46
    tt
    0.46
    state
    0.46
    Activations Density 0.000%

    No Known Activations