© 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. 74291
    Prev
    Next
    INDEX
    Explanations

    hann, bann, chann, shann, nann

    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
     Therefore
    -3.05
    Now
    -3.02
     Because
    -2.91
     and
    -2.81
     This
    -2.77
    After
    -2.75
     While
    -2.69
     Rather
    -2.63
     Then
    -2.63
    大约
    -2.55
    POSITIVE LOGITS
    琑
    2.81
    艄
    2.80
    檠
    2.70
    quirer
    2.61
    AutoresizingMask
    2.59
    cising
    2.52
    跸
    2.52
    sistent
    2.44
    ↵↵
    2.39
     ')[
    2.39
    Activations Density 0.020%

    No Known Activations