© 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. 68635
    Prev
    Next
    INDEX
    Explanations

    ordering healthcare providers

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

    problematic pairings and personas

    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
    ب
    0.45
    },\
    0.44
    ijdens
    0.43
    is
    0.42
    r
    0.42
    六
    0.42
    瘧
    0.40
     Character
    0.40
    一张
    0.39
    ференциа
    0.39
    POSITIVE LOGITS
     bố
    0.50
     Giveaway
    0.49
     여기에
    0.47
     Theological
    0.46
    InnerText
    0.45
    ={`${
    0.45
     Ades
    0.44
     понял
    0.44
     OMB
    0.43
     胸
    0.43
    Activations Density 0.000%

    No Known Activations