© 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. 81563
    Prev
    Next
    INDEX
    Explanations

    band/bands

    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
    broker
    -0.69
     Broker
    -0.68
     Burke
    -0.68
    Broker
    -0.65
    uxe
    -0.65
    école
    -0.65
    ække
    -0.64
    bur
    -0.63
    プリン
    -0.63
     Certificado
    -0.62
    POSITIVE LOGITS
     band
    4.38
     bands
    4.28
    band
    3.25
    bands
    3.17
     Band
    3.05
    BAND
    2.98
     BAND
    2.95
    Band
    2.92
     Bands
    2.92
    Bands
    2.70
    Activations Density 0.101%

    No Known Activations