© 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. 10567
    Prev
    Next
    INDEX
    Explanations

    permanent tooth, professional help, elementary school, written form, mains power

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

    physical infrastructure and concepts

    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
    েইলি
    0.57
     επίσης
    0.54
     دہشت
    0.52
    禟
    0.52
     কলকাত
    0.52
     Gourmet
    0.51
     Ubisoft
    0.51
    税务
    0.51
     کاروب
    0.50
    赚
    0.50
    POSITIVE LOGITS
     (=
    0.68
    </h2>
    0.54
     floribus
    0.50
     epithelium
    0.49
     outgrowth
    0.48
     pernicious
    0.46
     こう
    0.46
     recapit
    0.45
     muscul
    0.45
     これ
    0.44
    Activations Density 0.062%

    No Known Activations