© 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. 40840
    Prev
    Next
    INDEX
    Explanations

    I usually

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

    words followed by punctuation or connectors

    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
    赭
    0.42
    锕
    0.42
    δα
    0.41
    测
    0.40
     ไม
    0.39
    抉
    0.39
    ▐
    0.39
    iced
    0.39
    药
    0.39
    ued
    0.38
    POSITIVE LOGITS
     administrations
    0.55
     Kazan
    0.54
     hierarchies
    0.51
     academia
    0.51
     Gregorio
    0.49
     whistles
    0.48
     dynasties
    0.48
     leaders
    0.47
     entertainer
    0.47
     juniors
    0.46
    Activations Density 0.000%

    No Known Activations