© 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. 78338
    Prev
    Next
    INDEX
    Explanations

    words following punctuation

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

    punctuation and separators

    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
     Dieses
    0.54
    ,
    0.48
     Inoltre
    0.47
     Toutefois
    0.47
     Nachdem
    0.46
    mu
    0.45
     যাইহোক
    0.45
    ě
    0.45
    );
    0.44
     echter
    0.44
    POSITIVE LOGITS
    อยู่ใน
    0.49
    築
    0.45
    ທີ່
    0.45
    스가
    0.45
    Gosudarstvennyj
    0.45
     gastronomic
    0.44
    טי
    0.43
    に対する
    0.43
     ಇರುವ
    0.42
    או
    0.42
    Activations Density 0.058%

    No Known Activations