© 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. 22-GEMMASCOPE-RES-131K
    7. 73053
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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_22/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
    lectricité
    -0.99
    Jenis
    -0.99
     manualidades
    -0.99
     redonda
    -0.98
     dévo
    -0.97
     bienes
    -0.95
    Bahan
    -0.95
     when
    -0.91
    Kondisi
    -0.91
     mochilas
    -0.90
    POSITIVE LOGITS
     his
    1.02
     they
    1.01
     himself
    0.98
     निम्नलिखित
    0.91
    ity
    0.91
     such
    0.91
    outWeight
    0.90
     a
    0.90
     them
    0.90
     unbelievably
    0.89
    Activations Density 0.016%

    No Known Activations