© 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. 97217
    Prev
    Next
    INDEX
    Explanations

    specific concepts and domains

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

    students entering fields, extract file fields

    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
     Energ
    0.52
     ตั้ง
    0.51
     And
    0.49
     грошы
    0.49
    เอง
    0.48
    蒨
    0.48
     використо
    0.48
     Clermont
    0.47
    بن
    0.47
    兩種
    0.47
    POSITIVE LOGITS
    hti
    0.47
    )][
    0.43
    atches
    0.43
    incorporated
    0.42
     SESSION
    0.42
     выступ
    0.41
     hunts
    0.41
     reprieve
    0.41
    Toolbar
    0.41
     khắc
    0.40
    Activations Density 0.001%

    No Known Activations