© 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. 59942
    Prev
    Next
    INDEX
    Explanations

    s/c or s/

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

    S followed by punctuation or specific arguments

    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
    卤
    0.60
    檸
    0.59
    ดิจ
    0.59
    าว
    0.58
     जोश
    0.58
    وم
    0.57
    谜
    0.57
    zuführen
    0.57
     działal
    0.56
    าย
    0.56
    POSITIVE LOGITS
     S
    0.73
    ብስብ
    0.58
    a
    0.56
    cl
    0.55
    one
    0.55
    i
    0.54
     s
    0.54
    are
    0.54
     §
    0.54
     силы
    0.54
    Activations Density 0.158%

    No Known Activations