© 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. 69958
    Prev
    Next
    INDEX
    Explanations

    historical novels

    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
     totalPrice
    -0.91
    Ϝ
    -0.83
     терро
    -0.82
    😿
    -0.78
    totalPrice
    -0.78
     noticeably
    -0.78
     esos
    -0.77
    🍥
    -0.77
    leu
    -0.76
    卸载
    -0.76
    POSITIVE LOGITS
     historical
    1.08
    Historical
    1.02
     атмосфер
    0.91
     Historical
    0.89
     romanzo
    0.85
    Истори
    0.84
    HISTOR
    0.84
     истори
    0.80
    strictEqual
    0.78
     historische
    0.77
    Activations Density 0.042%

    No Known Activations