© 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. 30707
    Prev
    Next
    INDEX
    Explanations

    Katy area locations

    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
     canning
    -0.78
     causa
    -0.78
     skład
    -0.74
    Manuel
    -0.72
     óp
    -0.71
     Blind
    -0.71
    зино
    -0.71
     Arri
    -0.70
    Blind
    -0.70
    uset
    -0.69
    POSITIVE LOGITS
    시아
    0.92
     Woodlands
    0.86
    outen
    0.80
     Sienna
    0.78
     suya
    0.77
     Katy
    0.75
    mitir
    0.73
    bras
    0.72
     Cinco
    0.71
    setList
    0.71
    Activations Density 0.025%

    No Known Activations