© 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. 109410
    Prev
    Next
    INDEX
    Explanations

    financial transactions and investment

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

    time duration and status

    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
    ètement
    0.50
    ቆ
    0.48
     สิง
    0.48
    dziel
    0.46
    胿
    0.45
    討
    0.45
    Attrition
    0.44
    əri
    0.44
    の開発
    0.44
    ху
    0.43
    POSITIVE LOGITS
     tariff
    0.56
     Toll
    0.54
    0.54
     garantia
    0.49
     altri
    0.49
     card
    0.48
     cash
    0.48
     +
    0.46
     redacted
    0.46
     Certificate
    0.46
    Activations Density 0.000%

    No Known Activations