© 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. 55867
    Prev
    Next
    INDEX
    Explanations

    period followed by capitalized word

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

    self. attribute or method

    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
    ğiniz
    0.55
     satisfactor
    0.53
     rozwiąz
    0.51
    ంత
    0.51
    ⌵
    0.51
    ذور
    0.50
    ایات
    0.50
    robespierre
    0.50
    নির্ব
    0.50
    NeedConnect
    0.50
    POSITIVE LOGITS
     make
    0.64
     a
    0.60
     be
    0.58
    ud
    0.55
     is
    0.54
    ot
    0.53
    est
    0.53
     amm
    0.53
    ur
    0.53
     get
    0.53
    Activations Density 0.001%

    No Known Activations