© 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. 31703
    Prev
    Next
    INDEX
    Explanations

    copyright notices and licenses

    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
    Giovanni
    -0.77
    olidated
    -0.69
     uppgifter
    -0.69
     Attractions
    -0.68
     Giovanni
    -0.68
    ffè
    -0.67
    Ϣ
    -0.67
    saying
    -0.66
    قه
    -0.66
    Crom
    -0.66
    POSITIVE LOGITS
     Ether
    0.75
    演示
    0.73
    碚
    0.73
     てい
    0.71
     Permit
    0.68
    цина
    0.67
     cau
    0.66
    如果没有
    0.66
     небе
    0.65
     County
    0.64
    Activations Density 0.054%

    No Known Activations