© 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. 21900
    Prev
    Next
    INDEX
    Explanations

    shows date and value

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

    omitting

    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
     high
    0.49
    (
    0.49
     radiology
    0.48
     minimally
    0.48
     vc
    0.48
     biomedical
    0.47
     modeling
    0.47
     (\
    0.47
     spandex
    0.46
    顶
    0.46
    POSITIVE LOGITS
    くれます
    0.48
    삭제
    0.47
     olvidado
    0.46
    esta
    0.45
    Valor
    0.45
    义务
    0.44
     дату
    0.44
    给自己
    0.43
    罢了
    0.43
    valor
    0.42
    Activations Density 0.000%

    No Known Activations