© 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. 228519
    Prev
    Next
    INDEX
    Explanations

    particle physics 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
     Atmospheric
    0.46
     ν
    0.46
     ${\
    0.46
     خز
    0.46
    τ
    0.44
     putative
    0.43
     perturbed
    0.43
     ruthenium
    0.42
     scrut
    0.42
     sedimentary
    0.42
    POSITIVE LOGITS
    汜
    0.54
     jails
    0.53
    🍭
    0.52
    myCollision
    0.51
     उर्दू
    0.50
    🥊
    0.50
    लीट
    0.49
     стрель
    0.48
    दस
    0.48
     अर्जुन
    0.47
    Activations Density 0.006%

    No Known Activations