© 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. 46689
    Prev
    Next
    INDEX
    Explanations

    astronomical bursts and flares

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

    cosmic energetic phenomena

    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
     европей
    0.50
     परसेंटेज
    0.48
    猢
    0.47
     породы
    0.46
    ષ્ય
    0.45
    🕸
    0.45
    inputSet
    0.45
    娣
    0.44
     Percolation
    0.44
    axie
    0.44
    POSITIVE LOGITS
     view
    0.49
     ablation
    0.49
     bip
    0.45
    view
    0.43
     emitter
    0.42
     fluctu
    0.42
     fluctuating
    0.42
    flare
    0.42
     emissions
    0.41
     viewed
    0.41
    Activations Density 0.019%

    No Known Activations