© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 31988
    Prev
    Next
    INDEX
    Explanations

    average and sum along axis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     quản
    0.38
    ̹
    0.38
     এটির
    0.37
    机械
    0.37
    दारी
    0.36
     உருவாக்க
    0.36
    主要的
    0.36
     nigdy
    0.36
     இவற்ற
    0.36
    报警
    0.35
    POSITIVE LOGITS
     across
    0.59
    沿
    0.55
    Across
    0.55
    across
    0.53
     dim
    0.52
     Across
    0.50
     Axis
    0.50
     reducing
    0.50
     reduce
    0.49
    Axis
    0.49
    Activations Density 0.002%

    No Known Activations