© 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. 9063
    Prev
    Next
    INDEX
    Explanations

    This is a

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

    this is a

    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
     daí
    0.42
    нде
    0.40
    Además
    0.40
    鷺
    0.39
    ://"
    0.38
     erkannt
    0.38
    роде
    0.38
    这一切
    0.38
    сное
    0.38
    쾅
    0.38
    POSITIVE LOGITS
     리뷰
    0.52
     prettier
    0.50
     scoped
    0.47
    精品
    0.44
     pliable
    0.44
     server
    0.43
     NOT
    0.43
     USED
    0.43
    Xiv
    0.43
    प्ली
    0.43
    Activations Density 0.016%

    No Known Activations