© 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. 12509
    Prev
    Next
    INDEX
    Explanations

    punctuation and "appropriate"

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

    dialogue starters and 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
    Kelas
    0.34
    Ꮽ
    0.33
    เว็บไซต์
    0.33
    dasarkan
    0.32
    <unused2047>
    0.32
    Classe
    0.32
    戈
    0.32
    ٨
    0.32
    <unused969>
    0.32
    诺
    0.31
    POSITIVE LOGITS
     BUT
    0.33
     Ah
    0.31
    0.31
     But
    0.30
     nếu
    0.30
     Bs
    0.30
     eğer
    0.30
     Wool
    0.30
     OB
    0.29
     Para
    0.29
    Activations Density 0.022%

    No Known Activations