© 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. 161502
    Prev
    Next
    INDEX
    Explanations

    about or since

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

    words preceding punctuation

    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
     ova
    0.49
     hypogly
    0.47
    казать
    0.47
     KIA
    0.47
     (
    0.46
     saab
    0.46
     SVC
    0.46
     roving
    0.46
     on
    0.46
     trainee
    0.46
    POSITIVE LOGITS
     ഭാ
    0.57
     ऊंचाई
    0.56
    BtnUp
    0.56
     കാണ
    0.55
     രീതി
    0.54
     :=\
    0.53
    dimensioni
    0.53
    𝗙
    0.53
     ഇത്തരം
    0.52
     സൃഷ്ട
    0.52
    Activations Density 0.001%

    No Known Activations