© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10993
    Prev
    Next
    INDEX
    Explanations

    optimizer state explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    णिज्य
    2.58
    穰
    2.40
    валі
    2.36
    ろしく
    2.33
    产权
    2.31
     patrimonio
    2.30
    ப்பன்
    2.29
     найкра
    2.28
    ದುಕೊಳ್ಳ
    2.24
    事項
    2.22
    POSITIVE LOGITS
    nog
    1.85
    n
    1.53
    ื่น
    1.52
    nun
    1.51
    dik
    1.51
    nj
    1.47
    tart
    1.46
    diagram
    1.46
    eless
    1.45
    ters
    1.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.