© 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. 47840
    Prev
    Next
    INDEX
    Explanations

    Neurotypical or NeuroDivergent

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

    differential equations

    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
    <0x0D>
    0.54
     grantResults
    0.48
    Filed
    0.47
     tyto
    0.45
     Filed
    0.44
    filed
    0.44
     Podcasts
    0.42
    ({});
    0.42
    琛
    0.42
     internet
    0.41
    POSITIVE LOGITS
     հետ
    0.47
     millón
    0.45
     résultat
    0.45
     ⚫
    0.44
     electrónicos
    0.44
     încep
    0.43
     corpos
    0.42
     überras
    0.42
    études
    0.42
    स्ट्रेल
    0.41
    Activations Density 0.000%

    No Known Activations