© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 105722
    Prev
    Next
    INDEX
    Explanations

    quarterly newsletter

    np_acts-logits-general · gemini-2.5-flash-lite

    range of options or topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     आता
    0.52
     ব্যক্তিত্ব
    0.49
     záz
    0.48
    ಾಯಿತು
    0.47
    骯
    0.46
     其他
    0.46
    婊
    0.46
    cings
    0.46
    妣
    0.46
     Specifications
    0.45
    POSITIVE LOGITS
    p
    0.53
    td
    0.51
    URL
    0.51
    mid
    0.50
     tremor
    0.50
    ティ
    0.49
    to
    0.48
    ري
    0.48
    р
    0.48
    ld
    0.47
    Activations Density 0.000%

    No Known Activations