© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14954
    Prev
    Next
    INDEX
    Explanations

    financial transactions, market data, dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     حقی
    1.16
     ջ
    1.12
    Flagge
    1.02
    争取
    1.00
    TestAction
    1.00
     semoga
    1.00
     Aufmerksamkeit
    0.99
    impse
    0.98
     minta
    0.98
    amingo
    0.98
    POSITIVE LOGITS
     supplemented
    0.86
    er
    0.85
    в
    0.85
     computer
    0.83
    н
    0.82
    лишком
    0.78
    М
    0.77
     async
    0.76
    e
    0.76
    b
    0.75
    Activations Density 0.000%

    No Known Activations