© 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. 124542
    Prev
    Next
    INDEX
    Explanations

    definitions, testify, prudent, secure

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

    specific topics or entities

    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
     muse
    0.43
     henüz
    0.42
     vagu
    0.41
    僅
    0.41
    咳
    0.41
     quantify
    0.41
     egyik
    0.41
     tath
    0.41
    鶏
    0.41
     psychiat
    0.40
    POSITIVE LOGITS
     Insurance
    0.47
     Prior
    0.43
     কলকাত
    0.42
    ujemy
    0.42
     Vargas
    0.42
    ceğiz
    0.41
     Alba
    0.40
    owanej
    0.40
     Ambassadors
    0.40
     BASE
    0.39
    Activations Density 0.001%

    No Known Activations