© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77872
    Prev
    Next
    INDEX
    Explanations

    show or hide elements

    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
    Not in Any Lists

    No Comments

    Negative Logits
    assertRaises
    -0.84
    ဂ
    -0.78
    icherheit
    -0.76
    vän
    -0.75
     gastronom
    -0.74
     küpe
    -0.73
    抜け
    -0.73
    діо
    -0.72
     Konzept
    -0.71
    angal
    -0.71
    POSITIVE LOGITS
     visibility
    4.34
     visible
    4.16
    Visible
    3.61
    visible
    3.59
     Visibility
    3.48
    visibility
    3.47
     Visible
    3.44
    setVisible
    3.33
    Visibility
    3.31
    setVisibility
    3.16
    Activations Density 0.111%

    No Known Activations