© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159790
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

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

    punctuation question mark

    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
    Ꮦ
    0.61
    decoder
    0.54
    ЕН
    0.54
    Ꭷ
    0.52
    ホン
    0.51
    ЕНИ
    0.51
    LOTRE
    0.51
    𝔹
    0.51
    ᴊ
    0.50
    traction
    0.50
    POSITIVE LOGITS
     However
    0.61
     It
    0.59
     Tuttavia
    0.58
     Its
    0.56
     Ancak
    0.56
     Namun
    0.54
     If
    0.53
     Inoltre
    0.52
     In
    0.51
     But
    0.50
    Activations Density 0.055%

    No Known Activations