© 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. 95487
    Prev
    Next
    INDEX
    Explanations

    event series, documentary entitled, survive post

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

    variable amendments

    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
     §
    0.47
     書
    0.44
     bent
    0.43
     Texto
    0.43
     bitterly
    0.43
     Commod
    0.42
     cations
    0.42
    ശ്ശ
    0.42
     கீழ
    0.42
     interrupts
    0.42
    POSITIVE LOGITS
    音乐
    0.51
    钀
    0.49
    预计
    0.48
    专辑
    0.48
     каждая
    0.48
    计划
    0.48
    开始
    0.47
    过滤
    0.47
    ंत्रित
    0.46
     ఉంటాయి
    0.46
    Activations Density 0.001%

    No Known Activations