© 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. 69787
    Prev
    Next
    INDEX
    Explanations

    sequences after common words

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

    token following 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
     اللاعب
    0.57
    átku
    0.50
    夲
    0.50
    ते
    0.50
    かったです
    0.49
     équipements
    0.49
    ರೇ
    0.49
    दारा
    0.48
    鯢
    0.48
    ارق
    0.48
    POSITIVE LOGITS
    f
    0.50
     되겠
    0.47
     shall
    0.46
     may
    0.45
     precedes
    0.42
                               
    0.41
     Margaret
    0.41
     preserving
    0.41
     preserves
    0.41
     </
    0.40
    Activations Density 0.000%

    No Known Activations