© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149952
    Prev
    Next
    INDEX
    Explanations

    fixed income and rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    定番
    0.92
     `<=
    0.88
     recklessly
    0.88
    觥
    0.86
     northeastern
    0.86
    듕
    0.84
     staples
    0.84
    caling
    0.84
     favoritos
    0.83
     اعزائي
    0.82
    POSITIVE LOGITS
    Ad
    0.92
    Export
    0.91
    Train
    0.84
    Immun
    0.81
    C
    0.78
    Antib
    0.77
    Pres
    0.76
    Patient
    0.76
    Stand
    0.76
    Operation
    0.75
    Activations Density 0.001%

    No Known Activations