© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147132
    Prev
    Next
    INDEX
    Explanations

    dfrac, percentages, financial transactions

    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
     ~
    0.87
     runtime
    0.82
     ~.
    0.80
     (~
    0.79
     stereotypes
    0.76
     Lorena
    0.76
    ～～
    0.75
    (~
    0.75
     ~,
    0.75
     basin
    0.74
    POSITIVE LOGITS
    dfrac
    1.12
    Percent
    1.03
     Percent
    0.97
    Http
    0.91
    percent
    0.90
    .’’
    0.87
    .''
    0.85
    PERCENT
    0.84
     ‌
    0.82
    ਼
    0.82
    Activations Density 0.000%

    No Known Activations