© 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. 81418
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

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

    latex image commands

    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
     ایپل
    0.45
     ادائیگی
    0.44
    ު
    0.42
     mitophagy
    0.41
     जिससे
    0.41
     όταν
    0.40
     Serif
    0.39
     قرض
    0.39
     ڏ
    0.39
     crédito
    0.39
    POSITIVE LOGITS
     并
    0.44
     W
    0.43
     arcu
    0.42
    并
    0.42
     et
    0.42
    tk
    0.42
    這樣的
    0.41
     such
    0.41
    DUCED
    0.40
    4
    0.40
    Activations Density 0.000%

    No Known Activations