© 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. 134206
    Prev
    Next
    INDEX
    Explanations

    light painting named

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

    Type 1 Bare-Metal hypervisors

    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
    PAGE
    0.49
    POL
    0.49
    AVAILABLE
    0.47
    WELCOME
    0.45
    ب
    0.45
    TIME
    0.45
    VIDEO
    0.44
     believes
    0.43
    SRPI
    0.43
     apne
    0.43
    POSITIVE LOGITS
    雑誌
    0.50
    秞
    0.50
     رعایت
    0.49
    ouchers
    0.48
     शक
    0.46
    avacanam
    0.46
    粙
    0.45
    riteria
    0.45
    此同时
    0.45
     бүт
    0.45
    Activations Density 0.001%

    No Known Activations