© 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. 21336
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by new sentence start

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

    end of sentence 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
    硋
    0.29
    ״
    0.28
    ́t
    0.28
    етра
    0.27
    ี
    0.27
    ДО
    0.26
    ТС
    0.26
    бер
    0.26
    克斯
    0.26
    〝
    0.26
    POSITIVE LOGITS
     with
    0.28
     Kee
    0.27
     Sienna
    0.26
     mivel
    0.26
     u
    0.26
     i
    0.25
    များနှင့်
    0.25
     M
    0.25
     allow
    0.25
     nghi
    0.25
    Activations Density 0.179%

    No Known Activations