© 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. 201053
    Prev
    Next
    INDEX
    Explanations

    Neuschwanstein

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

    behaves responsibly

    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
    gle
    0.43
    笫
    0.43
     ትንሽ
    0.42
     কাগজ
    0.41
    γων
    0.41
    視覺
    0.40
     міні
    0.40
    旁邊
    0.39
    begin
    0.39
    焊接
    0.39
    POSITIVE LOGITS
     użytk
    0.55
    шкой
    0.50
    owi
    0.49
    "]')
    0.49
     atividade
    0.48
    /",
    0.47
     வாழ்க்கை
    0.47
     podr
    0.46
     powered
    0.46
     amenazas
    0.46
    Activations Density 0.001%

    No Known Activations