© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118083
    Prev
    Next
    INDEX
    Explanations

    Indian names and places

    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
     النار
    -0.81
     torn
    -0.75
     pins
    -0.74
    ˶
    -0.71
     caus
    -0.70
    BY
    -0.67
    かれている
    -0.67
     oblic
    -0.67
     काम
    -0.67
     te
    -0.67
    POSITIVE LOGITS
    Technische
    0.83
    (",
    0.77
    iments
    0.76
    ."-
    0.75
    قية
    0.75
    ⓜ
    0.73
    stellung
    0.73
    ᶰ
    0.73
    Verdict
    0.72
    pantalón
    0.72
    Activations Density 0.008%

    No Known Activations