© 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. 91892
    Prev
    Next
    INDEX
    Explanations

    high accuracy

    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
     sympathique
    -0.81
     tivesse
    -0.80
    骇
    -0.76
    ólica
    -0.76
    getPassword
    -0.74
     Universidades
    -0.74
    谚
    -0.73
    笞
    -0.73
    市的
    -0.73
    Laurent
    -0.72
    POSITIVE LOGITS
     accuracy
    4.81
     precision
    4.56
     accurate
    4.25
     Accuracy
    3.73
    accuracy
    3.73
    precision
    3.70
     precise
    3.64
    Accuracy
    3.64
    accurate
    3.45
     precisión
    3.42
    Activations Density 0.168%

    No Known Activations