Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 180
    Prev
    Next
    INDEX
    Explanations

    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_16_width_16k_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
     and
    0.66
    ft
    0.65
     are
    0.63
    的
    0.61
    ра
    0.59
     in
    0.58
    σ
    0.52
     as
    0.52
    માં
    0.50
    ง
    0.50
    POSITIVE LOGITS
    accouchement
    0.58
     Оба
    0.57
    Doesn
    0.55
     ਵਿ
    0.54
    Increment
    0.54
    doesn
    0.54
    ILL
    0.54
    ASER
    0.54
    Whit
    0.53
    Emulator
    0.53
    Activations Density 0.000%

    No Known Activations