© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76826
    Prev
    Next
    INDEX
    Explanations

    words following 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-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PON
    0.36
     distinctions
    0.35
     зача
    0.35
    layers
    0.34
    佩
    0.34
     distractions
    0.33
     postav
    0.33
    SOUR
    0.33
    лору
    0.33
     пора
    0.33
    POSITIVE LOGITS
    $.)
    0.38
    érc
    0.37
     noticing
    0.35
    agg
    0.35
    อนไลน์
    0.34
     ছাপা
    0.33
     hui
    0.32
    clu
    0.32
     ticket
    0.32
    िटर
    0.32
    Activations Density 0.003%

    No Known Activations