© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1100
    Prev
    Next
    INDEX
    Explanations

    calculation and computation

    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_9_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
    م
    3.31
    ى
    3.12
    ьте
    3.01
    HING
    2.87
     averse
    2.86
     shuffling
    2.75
    ям
    2.70
    ство
    2.70
    례
    2.59
    こと
    2.58
    POSITIVE LOGITS
    و
    4.54
    en
    3.52
    dresser
    3.30
    ே
    3.28
    ла
    3.21
    udsman
    3.17
    in
    3.12
    ০
    3.12
     چې
    3.12
    ន់
    3.08
    Activations Density 1.937%

    No Known Activations