© 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. 37163
    Prev
    Next
    INDEX
    Explanations

    sentence endings

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

    sentence ending 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
    𝚕
    0.44
     fancy
    0.44
     fí
    0.43
    ้อ
    0.40
    fancy
    0.40
     tortoise
    0.40
     genannten
    0.40
    SIR
    0.38
     CLP
    0.38
    Ī
    0.38
    POSITIVE LOGITS
    。
    0.84
    ‌.
    0.83
    .;
    0.77
    ။
    0.75
    ።
    0.75
    .).
    0.68
    .[[
    0.68
    ۔
    0.68
    。.
    0.67
    .),
    0.66
    Activations Density 0.115%

    No Known Activations