© 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. 158685
    Prev
    Next
    INDEX
    Explanations

    Rogozin, John, migrants, next step

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

    learning and handling data

    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
    ausal
    0.50
    Вот
    0.48
    드의
    0.46
    торов
    0.46
    ட்ரோ
    0.45
    มาชิก
    0.45
     inhabiting
    0.45
    恹
    0.45
    товая
    0.44
    тории
    0.44
    POSITIVE LOGITS
    HANDLE
    0.50
    塑
    0.50
    contra
    0.43
    在哪
    0.41
    BANNER
    0.41
    ”）
    0.40
    太空
    0.40
    下一步
    0.39
     కృషి
    0.39
    prototype
    0.38
    Activations Density 0.008%

    No Known Activations