© 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. 11652
    Prev
    Next
    INDEX
    Explanations

    Barcode, referred to

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

    response preambles

    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
     seuls
    0.31
    <unused96>
    0.30
     médioc
    0.29
    <unused29>
    0.29
    आवेदन
    0.29
     wobei
    0.28
     seules
    0.28
    <unused10>
    0.27
     ayatan
    0.27
    <unused27>
    0.27
    POSITIVE LOGITS
    1
    0.27
     C
    0.25
     I
    0.25
    &
    0.25
    ULAR
    0.25
    _
    0.25
    G
    0.25
      
    0.24
     J
    0.24
    W
    0.24
    Activations Density 0.792%

    No Known Activations