© 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. 117620
    Prev
    Next
    INDEX
    Explanations

    dynamically when heated

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

    tales exploring deep reading aloud

    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
    therapy
    0.46
    鈾
    0.46
     laboratoire
    0.45
    𒁀
    0.45
    ラボ
    0.45
    ಿನಿ
    0.44
     財布
    0.44
     عمد
    0.44
     willfully
    0.44
     प्रयोगशाला
    0.44
    POSITIVE LOGITS
     Paf
    0.44
     ৬৬
    0.44
     Ole
    0.43
    [
    0.43
     इसे
    0.42
     Asus
    0.42
    লিউ
    0.42
     tertiary
    0.42
    全ての
    0.42
     этом
    0.41
    Activations Density 0.001%

    No Known Activations