© 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. 150817
    Prev
    Next
    INDEX
    Explanations

    then extract

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

    Base Case; Packages; CLI; ABV

    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
    َ
    0.48
     ㅏ
    0.46
    聯盟
    0.46
     SEASON
    0.45
     FOOT
    0.45
    า
    0.44
     commentary
    0.44
    樂
    0.43
    րա
    0.43
    WITH
    0.42
    POSITIVE LOGITS
     सुझा
    0.61
    ifical
    0.48
     EMS
    0.47
    ដែលអាច
    0.47
     étamines
    0.46
     ayudas
    0.46
    ulated
    0.46
     Moul
    0.46
    educt
    0.45
     sillons
    0.45
    Activations Density 0.000%

    No Known Activations