© 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. 116660
    Prev
    Next
    INDEX
    Explanations

    companies, jobs, pages, CVs

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

    terrible fate, tetrahedral cells, I am

    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
    личество
    0.54
    混凝
    0.52
     इवेंट
    0.50
     मसल्स
    0.49
    觊
    0.49
     साधा
    0.49
    ముఖ
    0.48
     शव
    0.48
    纨
    0.47
    ्योर
    0.47
    POSITIVE LOGITS
     Trento
    0.50
     wed
    0.45
     ro
    0.44
     don
    0.42
     tom
    0.41
     ocean
    0.39
     bureau
    0.39
     cast
    0.39
     å
    0.39
     tob
    0.39
    Activations Density 0.000%

    No Known Activations