© 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. 99485
    Prev
    Next
    INDEX
    Explanations

    peace be

    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
    Department
    -0.87
     Department
    -0.85
    Fields
    -0.82
    entiel
    -0.79
     Scheme
    -0.78
     FIELD
    -0.78
    Resources
    -0.77
     field
    -0.74
     Resources
    -0.74
    resource
    -0.74
    POSITIVE LOGITS
    ップ
    0.68
    ventilated
    0.68
    ที
    0.64
    逛
    0.62
     obscured
    0.61
     Pana
    0.61
    労
    0.60
    assertRaises
    0.60
     说明
    0.58
     tới
    0.57
    Activations Density 0.066%

    No Known Activations