© 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. 5279
    Prev
    Next
    INDEX
    Explanations

    location, time, or quantity sequences

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

    concession and consequence connectors

    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
     图
    0.40
    Animated
    0.38
    Bootstrap
    0.38
    图
    0.38
     arcs
    0.36
     arcane
    0.36
    关键字
    0.35
    的
    0.35
     types
    0.35
     typography
    0.35
    POSITIVE LOGITS
     Menteri
    0.42
     परिस्थिति
    0.41
     Entretanto
    0.41
     そんな
    0.40
     Međutim
    0.40
     dirigentes
    0.40
     Notwithstanding
    0.40
     Governo
    0.39
    とはいえ
    0.39
     Devlet
    0.38
    Activations Density 0.024%

    No Known Activations