© 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. 92113
    Prev
    Next
    INDEX
    Explanations

    specialist physician

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

    city settlements, resting minds

    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
    卫生
    0.50
     Peral
    0.47
     Drone
    0.46
     Conspiracy
    0.45
    贾
    0.44
    㚅
    0.44
    stice
    0.43
     Aby
    0.41
     Humanity
    0.41
    人性
    0.41
    POSITIVE LOGITS
    ৪৭
    0.49
    බා
    0.46
    algar
    0.45
    ointers
    0.45
    elsius
    0.44
     indented
    0.44
    кг
    0.44
    igste
    0.44
     diagrama
    0.43
     '.';
    0.43
    Activations Density 0.001%

    No Known Activations