© 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. 154534
    Prev
    Next
    INDEX
    Explanations

    search and customize

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

    Cards Against Humanity

    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
     کاروبار
    0.49
    ext
    0.48
     අතර
    0.45
    ем
    0.45
    ɛ
    0.44
    axi
    0.43
    abe
    0.41
    viendo
    0.41
    actus
    0.41
     maximally
    0.41
    POSITIVE LOGITS
    cU
    0.50
     annuel
    0.50
    数
    0.48
    ু
    0.48
    ج
    0.48
    歡迎
    0.47
    ্বল
    0.47
    люб
    0.47
    Съ
    0.46
    Пу
    0.46
    Activations Density 0.000%

    No Known Activations