© 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. 43624
    Prev
    Next
    INDEX
    Explanations

    Carthaginian history and conflict

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

    commands and tactics

    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
     रोटी
    0.47
     ഇവ
    0.47
    讀
    0.46
     katanya
    0.46
     huk
    0.46
     गोष्ट
    0.46
     ikki
    0.45
     ikke
    0.44
    ॉन्स
    0.44
     muitos
    0.44
    POSITIVE LOGITS
    s
    0.55
    зер
    0.45
     deepened
    0.42
     preceded
    0.42
     Col
    0.39
    绵
    0.39
     supplemented
    0.38
    áneamente
    0.38
     Desar
    0.38
     lowered
    0.37
    Activations Density 0.000%

    No Known Activations