© 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. 30548
    Prev
    Next
    INDEX
    Explanations

    container

    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
    ριά
    -0.82
     hacerte
    -0.74
    থ্য
    -0.74
    udin
    -0.72
    ENODEV
    -0.72
    Packaged
    -0.70
    Pkg
    -0.69
     moverse
    -0.68
     Package
    -0.68
     Tolstoy
    -0.68
    POSITIVE LOGITS
     bowl
    3.83
     bowls
    2.92
     Bowl
    2.84
    bowl
    2.83
    Bowl
    2.50
     Bowls
    2.03
     BOW
    1.81
     basin
    1.73
    BOW
    1.61
    碗
    1.55
    Activations Density 0.017%

    No Known Activations