© 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. 65118
    Prev
    Next
    INDEX
    Explanations

    nest box or United States

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

    intended to be, ensures students, neglect the, make meaningful

    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
    ɩ
    0.55
    پ
    0.52
     ಜಾ
    0.50
    ႁ
    0.50
    金
    0.48
    有可能
    0.48
    ícul
    0.47
    住宿
    0.47
    ᱤ
    0.47
    栢
    0.46
    POSITIVE LOGITS
     تلك
    0.45
     vybaven
    0.41
     컴퓨
    0.41
     cognizant
    0.37
     سمجھتے
    0.36
     обяза
    0.36
    телю
    0.36
     الأمريكية
    0.36
    verständ
    0.35
    eseen
    0.35
    Activations Density 0.000%

    No Known Activations