© 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. 61994
    Prev
    Next
    INDEX
    Explanations

    find their way

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

    learning, hobbies, and physical attributes

    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
     extranjero
    0.47
     ژوند
    0.47
     کال
    0.46
     ڈاؤن
    0.46
     usa
    0.46
     arrogant
    0.46
     komfort
    0.46
     ۶
    0.46
     selatan
    0.46
     ۸
    0.45
    POSITIVE LOGITS
    昉
    0.47
    延长
    0.45
    的时间
    0.44
    Numerator
    0.42
    持续
    0.41
     attén
    0.40
    财政
    0.40
    的点
    0.40
     χρόνο
    0.40
    多个
    0.39
    Activations Density 0.000%

    No Known Activations