© 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. 56097
    Prev
    Next
    INDEX
    Explanations

    internal components or processes

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

    medical treatment, videos, and occurrence

    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
    镜
    0.48
    繁
    0.47
     menacing
    0.45
    izate
    0.45
    类的
    0.45
    ضة
    0.44
    класс
    0.44
    да
    0.44
     đúng
    0.43
    魅
    0.43
    POSITIVE LOGITS
    radiative
    0.48
    heuristic
    0.46
    overall
    0.45
    inė
    0.45
    本科
    0.45
     رکن
    0.45
     borrower
    0.44
     Wallis
    0.44
    ার্জন
    0.43
     האל
    0.43
    Activations Density 0.000%

    No Known Activations