© 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. 10-GEMMASCOPE-RES-131K
    7. 59920
    Prev
    Next
    INDEX
    Explanations

    javadoc comments with description

    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
    ⢌
    -3.02
    ם
    -2.72
    鴆
    -2.63
    ₶
    -2.59
     eve
    -2.56
    小伙伴
    -2.55
     importantly
    -2.50
     夜景
    -2.48
    㩒
    -2.48
     vyroben
    -2.45
    POSITIVE LOGITS
    In
    3.52
    e
    3.41
    y
    3.31
    These
    3.08
    The
    2.91
    IN
    2.84
    This
    2.84
     It
    2.84
    At
    2.81
    To
    2.70
    Activations Density 0.011%

    No Known Activations