© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76815
    Prev
    Next
    INDEX
    Explanations

    code components or license

    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
     Limits
    -0.74
    Yue
    -0.72
     Yue
    -0.71
     wires
    -0.69
    faktor
    -0.68
    Documento
    -0.68
     sinon
    -0.67
    wires
    -0.66
    Wong
    -0.66
     tid
    -0.65
    POSITIVE LOGITS
     tannins
    0.73
    head
    0.73
     sculptural
    0.70
     llvm
    0.67
     проверя
    0.66
     viață
    0.64
    沼
    0.63
    
    0.63
     Checked
    0.63
     istitu
    0.63
    Activations Density 0.050%

    No Known Activations