© 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. 131040
    Prev
    Next
    INDEX
    Explanations

    time and places

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

    its definition or purpose

    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
    c
    0.44
     spieg
    0.43
     illustrations
    0.43
    manuel
    0.43
     khởi
    0.43
    县
    0.43
     oblique
    0.43
     embed
    0.42
    rul
    0.42
     equivalents
    0.42
    POSITIVE LOGITS
    Allora
    0.54
    În
    0.52
    Не
    0.52
    Полу
    0.50
    걍
    0.50
    Что
    0.50
    Ừ
    0.49
    Как
    0.49
    Produ
    0.49
    Нет
    0.49
    Activations Density 0.000%

    No Known Activations