© 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. 150937
    Prev
    Next
    INDEX
    Explanations

    words before punctuation or specific words

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

    And followed by the

    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
    Look
    0.55
    Language
    0.55
    We
    0.50
    И
    0.49
    م
    0.49
    נו
    0.49
    בר
    0.48
     Ту
    0.47
    語言
    0.47
    ας
    0.46
    POSITIVE LOGITS
    olytic
    0.48
     bilirubin
    0.48
     sufferers
    0.47
    ophylline
    0.47
    roidism
    0.46
     switchTo
    0.45
    xiety
    0.45
     প্রতিক্রি
    0.45
     pono
    0.44
     interplay
    0.44
    Activations Density 0.001%

    No Known Activations