© 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. 212381
    Prev
    Next
    INDEX
    Explanations

    repeat steps

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

    Continuous learning

    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
     గ్ర
    0.45
    ጋገብ
    0.45
     знаем
    0.44
    Cookies
    0.44
     आरबीआई
    0.44
    餅
    0.43
     зни
    0.42
    冊
    0.42
    tabControl
    0.42
     Express
    0.41
    POSITIVE LOGITS
    ła
    0.50
     Livermore
    0.49
    ุ
    0.48
    landı
    0.47
    yya
    0.47
     ㅏ
    0.46
     corro
    0.46
    łam
    0.46
    海の
    0.46
     sewer
    0.45
    Activations Density 0.001%

    No Known Activations