© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 89545
    Prev
    Next
    INDEX
    Explanations

    LaTeX code and features

    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/layer_16_width_262k_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
    ן
    0.93
    もら
    0.87
     ascertaining
    0.72
    "
    0.70
     Гри
    0.67
    ें
    0.66
    ಾಗಲೇ
    0.66
     Кто
    0.66
    }"
    0.65
     הראש
    0.65
    POSITIVE LOGITS
    a
    1.09
    ন
    1.00
    어
    1.00
     be
    0.92
    ă
    0.91
     مي
    0.89
    ᅵ
    0.89
    <0xAC>
    0.87
    ="
    0.87
    한
    0.87
    Activations Density 0.000%

    No Known Activations