© 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. 108268
    Prev
    Next
    INDEX
    Explanations

    class, method, type, fields

    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
    ilder
    -0.75
    zonych
    -0.73
     NSD
    -0.71
    Ỡ
    -0.70
     Emilia
    -0.69
     Inquirer
    -0.69
     colloc
    -0.69
    gion
    -0.69
    翁
    -0.69
    FixedSize
    -0.68
    POSITIVE LOGITS
     Class
    1.25
     Method
    1.05
    Class
    1.05
     Type
    0.94
     Constructor
    0.90
     method
    0.85
    Method
    0.85
     hubo
    0.82
     quicker
    0.81
    ETHOD
    0.79
    Activations Density 0.007%

    No Known Activations