© 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. 58042
    Prev
    Next
    INDEX
    Explanations

    introduces or follows specific terms

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

    program name, speed of, core positions

    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
    "];
    0.46
    篡
    0.41
    景象
    0.40
     chamado
    0.40
     njeg
    0.40
    ركه
    0.39
    特朗普
    0.39
    其
    0.39
     mankind
    0.39
     ennemis
    0.39
    POSITIVE LOGITS
    Sensor
    0.54
    ขนาด
    0.50
     Sensor
    0.49
     ขนาด
    0.48
     機能
    0.46
    ServiceModel
    0.44
    ENERGY
    0.44
    Ở
    0.44
    মূল
    0.44
     टेक्नोलॉजी
    0.44
    Activations Density 0.000%

    No Known Activations