© 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. 8631
    Prev
    Next
    INDEX
    Explanations

    or not

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

    negation or binary distinction

    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
    이자
    0.42
    ৫
    0.42
     aulas
    0.40
    장
    0.38
     ሥ
    0.37
     ヨ
    0.36
    ITATION
    0.36
    隂
    0.36
     iniciativas
    0.35
    য়
    0.35
    POSITIVE LOGITS
    否
    0.71
     not
    0.68
     NOT
    0.66
     else
    0.58
     नॉट
    0.56
    หรือไม่
    0.55
    nope
    0.54
     아닌
    0.52
     whatnot
    0.52
     नहीं
    0.52
    Activations Density 0.081%

    No Known Activations