© 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. 62274
    Prev
    Next
    INDEX
    Explanations

    quantifiers ending statements

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

    quantifying, selecting, or categorizing lists

    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
    িয়াল
    0.45
    ಿಯೂ
    0.44
    ʏ
    0.44
    这种
    0.42
    -)
    0.42
    ándola
    0.41
     Sachin
    0.41
     entanto
    0.41
    ㄉ
    0.41
    สุดท้าย
    0.40
    POSITIVE LOGITS
    ;
    0.82
    。
    0.73
    ؛
    0.73
    ।
    0.72
    ；
    0.72
    ။
    0.65
    ។
    0.64
    ،
    0.62
    !
    0.62
    ！
    0.60
    Activations Density 0.332%

    No Known Activations