© 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. 186661
    Prev
    Next
    INDEX
    Explanations

    foreign words and specific phrases

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

    contextualizing abstract concepts

    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
    us
    0.51
     have
    0.46
     immunized
    0.46
     opened
    0.45
     as
    0.44
     learned
    0.44
    I
    0.43
    index
    0.42
     actually
    0.41
    azard
    0.41
    POSITIVE LOGITS
    पुरम
    0.51
    ണാ
    0.51
    摄像
    0.50
     travailler
    0.49
     cámara
    0.49
     limpar
    0.48
     minif
    0.48
    挝
    0.48
     deixar
    0.48
     luoghi
    0.48
    Activations Density 0.001%

    No Known Activations