© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93584
    Prev
    Next
    INDEX
    Explanations

    plotting symbols or errors

    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
     sucre
    -0.79
    ')(
    -0.77
    مط
    -0.73
    Heute
    -0.71
    维度
    -0.69
    unteers
    -0.68
    لقد
    -0.68
     Hinds
    -0.68
    ولد
    -0.67
     näh
    -0.67
    POSITIVE LOGITS
     error
    2.56
     points
    2.41
     bars
    2.19
     symbols
    2.17
     Error
    2.14
    error
    2.08
     Symbols
    2.03
    symbols
    2.02
    points
    1.92
     Bars
    1.84
    Activations Density 0.040%

    No Known Activations