© 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. 170180
    Prev
    Next
    INDEX
    Explanations

    Server Plugin, last day, expand screen

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

    financial "long" or "zero day"

    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
     tj
    0.48
     inorganic
    0.46
    <0x89>
    0.46
     ＊
    0.46
     TJ
    0.45
     ionized
    0.45
     fxe
    0.44
     statesman
    0.44
     পেলে
    0.44
     invoicing
    0.44
    POSITIVE LOGITS
    閃
    0.44
    Indoor
    0.44
    Intu
    0.43
    Indigenous
    0.43
    лья
    0.43
    陳
    0.43
    ਆਂ
    0.42
     सहाय
    0.42
    Philadelphia
    0.42
     चलाई
    0.42
    Activations Density 0.006%

    No Known Activations