© 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. 219479
    Prev
    Next
    INDEX
    Explanations

    corporate colours

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

    sensitive data, community, ecosystem

    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
    ร
    0.52
    ोम
    0.49
     typos
    0.47
    ง
    0.47
    Հ
    0.46
     please
    0.46
     or
    0.45
     ambush
    0.44
    ट
    0.44
    颏
    0.44
    POSITIVE LOGITS
     Христос
    0.54
    dataSource
    0.49
    oloj
    0.47
    entend
    0.47
     Франция
    0.46
    protein
    0.46
    context
    0.46
    timestamp
    0.45
     বিপ্ল
    0.45
     SqlParameter
    0.44
    Activations Density 0.001%

    No Known Activations