© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33545
    Prev
    Next
    INDEX
    Explanations

    "Hamilton County" or "const nest" or "In gas"

    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
    TSD
    -0.85
     marten
    -0.77
    getExtras
    -0.75
    เอง
    -0.73
    мет
    -0.73
     تأ
    -0.73
     digest
    -0.73
    🥄
    -0.72
     blasted
    -0.72
     циф
    -0.71
    POSITIVE LOGITS
     OFFICE
    0.82
     lancia
    0.79
     rosso
    0.78
     caratteri
    0.78
     CHARACTERS
    0.77
     Glaubens
    0.76
     disegno
    0.76
    berra
    0.75
     parere
    0.75
    titutions
    0.74
    Activations Density 0.028%

    No Known Activations