© 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. 243229
    Prev
    Next
    INDEX
    Explanations

    initially, eventually, ad

    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
    単位
    0.54
    頹
    0.50
    這一
    0.48
    ื่อน
    0.48
    إذا
    0.48
    黾
    0.47
    産業
    0.46
    وف
    0.46
    ।...
    0.46
     повышения
    0.46
    POSITIVE LOGITS
    ad
    0.57
     Initially
    0.49
     있어서
    0.48
     Ad
    0.47
     Brawl
    0.47
     Invitational
    0.47
     Eventually
    0.46
     inicialmente
    0.46
     initially
    0.45
     Ana
    0.45
    Activations Density 0.000%

    No Known Activations