© 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. 1388
    Prev
    Next
    INDEX
    Explanations

    file paths and code structure

    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
    hints
    -0.72
    健康
    -0.70
    (+)
    -0.69
    <?,
    -0.68
    դ
    -0.67
     adalah
    -0.66
     significato
    -0.66
     Lagi
    -0.65
    Ifc
    -0.65
    Lifecycle
    -0.65
    POSITIVE LOGITS
    boe
    0.91
    自分も
    0.86
    acic
    0.82
     chảy
    0.80
    三個
    0.79
     proyección
    0.79
     diseñador
    0.78
    ところで
    0.78
    それから
    0.78
     universidad
    0.77
    Activations Density 0.008%

    No Known Activations