© 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. 10-GEMMASCOPE-RES-131K
    7. 69779
    Prev
    Next
    INDEX
    Explanations

    dates, centuries, BC/BCE

    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_10/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
    ейчас
    -1.76
    ቷ
    -1.70
    Cdt
    -1.67
     Mijn
    -1.60
    ureen
    -1.57
    鲞
    -1.55
    鵟
    -1.54
    ༣
    -1.52
     стоковые
    -1.50
    ᾐ
    -1.50
    POSITIVE LOGITS
    ↵
    1.99
    3
    1.98
    T
    1.89
    –
    1.80
    U
    1.80
    I
    1.77
    N
    1.77
    p
    1.75
    .”
    1.72
    >
    1.70
    Activations Density 0.084%

    No Known Activations