© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13106
    Prev
    Next
    INDEX
    Explanations

    performance and results

    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_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
    special
    0.73
    breakable
    0.72
     special
    0.70
     living
    0.70
     specials
    0.67
    primitive
    0.67
     eagerly
    0.66
    烈
    0.66
     punctual
    0.66
     make
    0.66
    POSITIVE LOGITS
     эффективность
    1.06
     Verbesser
    0.98
     eficiencia
    0.91
     Trials
    0.91
     эффективности
    0.90
     hiệu
    0.90
    绩效
    0.89
     Efficiency
    0.88
    效益
    0.88
     beneficios
    0.88
    Activations Density 0.001%

    No Known Activations