© 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. 77773
    Prev
    Next
    INDEX
    Explanations

    end of sentence or phrase

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

    punctuation and symbols

    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
     daher
    0.46
    但这
    0.43
     Portanto
    0.42
     quindi
    0.41
     যা
    0.41
    ভে
    0.41
     ayrıca
    0.38
    <0xB8>
    0.38
     Therefore
    0.38
     dabei
    0.38
    POSITIVE LOGITS
     comedies
    0.42
    ランプ
    0.39
    겅
    0.39
    TDto
    0.38
    吆
    0.38
    咆
    0.38
    梦想
    0.37
     প্রেমিক
    0.37
     polici
    0.37
     Thì
    0.37
    Activations Density 0.028%

    No Known Activations