© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62513
    Prev
    Next
    INDEX
    Explanations

    section headings or content anchors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     любого
    -0.92
     Eventually
    -0.82
     #
    -0.81
    probably
    -0.81
    色々な
    -0.81
     Upon
    -0.77
    seus
    -0.77
     these
    -0.75
    Estos
    -0.75
     seguramente
    -0.75
    POSITIVE LOGITS
    anchor
    1.18
    :~
    1.18
     section
    1.09
    Anchor
    1.08
    section
    1.07
    sth
    1.06
     heading
    1.00
    SECTION
    0.99
    Heading
    0.98
    sec
    0.94
    Activations Density 0.117%

    No Known Activations