© 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-16K
    7. 3560
    Prev
    Next
    INDEX
    Explanations

    Reinforcement Learning and resource estimation

    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_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
     Dem
    0.90
     dem
    0.88
    Dem
    0.85
    dem
    0.78
     그렇
    0.71
     Время
    0.70
     Ej
    0.70
    꼼
    0.68
     ਉਹ
    0.68
    এমন
    0.67
    POSITIVE LOGITS
     τησ
    0.80
     heran
    0.77
     des
    0.75
    ationen
    0.74
     kelu
    0.72
     της
    0.71
    消費
    0.71
     medication
    0.68
     अदा
    0.67
     und
    0.67
    Activations Density 0.137%

    No Known Activations