© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2949
    Prev
    Next
    INDEX
    Explanations

    The capital

    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_22_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
    subNav
    0.78
    iculis
    0.77
     미술
    0.76
     warehousing
    0.75
     상담
    0.75
    漳
    0.71
    欷
    0.71
     학습
    0.71
    事业单位
    0.71
     Intervals
    0.71
    POSITIVE LOGITS
     president
    2.14
     President
    2.03
     CEO
    1.96
    president
    1.95
     leader
    1.91
    President
    1.88
     presidente
    1.84
     Präsident
    1.82
     président
    1.80
    總統
    1.76
    Activations Density 0.870%

    No Known Activations