© 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. 107215
    Prev
    Next
    INDEX
    Explanations

    computer science and applications

    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
    戏剧
    -0.90
    木の
    -0.87
     других
    -0.86
     acadé
    -0.85
     yazar
    -0.83
     cocin
    -0.81
     
    -0.81
     วัด
    -0.81
     pode
    -0.81
     ellas
    -0.81
    POSITIVE LOGITS
    ised
    1.47
     aided
    1.31
     generated
    1.20
     science
    1.11
    ized
    1.02
     mediated
    1.02
     tomography
    1.02
    ization
    0.97
     skills
    0.96
    న్
    0.95
    Activations Density 0.045%

    No Known Activations