© 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. 116286
    Prev
    Next
    INDEX
    Explanations

    Texas cities and courts

    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
     formales
    -0.84
    ormon
    -0.76
     Oz
    -0.76
     italien
    -0.75
     recomendamos
    -0.75
     екс
    -0.73
     Tipper
    -0.72
    timento
    -0.71
     multiplication
    -0.71
    hancers
    -0.71
    POSITIVE LOGITS
     ボーダー
    0.81
    歴代
    0.77
    icato
    0.77
     saluto
    0.74
     Sacrific
    0.71
     クリア
    0.70
     UAS
    0.70
     dunque
    0.70
     levering
    0.69
     whoa
    0.69
    Activations Density 0.067%

    No Known Activations