© 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. 45511
    Prev
    Next
    INDEX
    Explanations

    musical bands and groups

    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
    гент
    -0.77
    onent
    -0.73
    מְ
    -0.72
     corporativa
    -0.71
    ricane
    -0.71
     teammate
    -0.71
    ClassPath
    -0.71
    ሴ
    -0.70
    леб
    -0.70
    Naphthalene
    -0.69
    POSITIVE LOGITS
     band
    4.38
     group
    4.16
     groups
    3.52
     bands
    3.42
    group
    3.02
    band
    2.81
     grupo
    2.81
     گروه
    2.78
    バンド
    2.72
     groupe
    2.70
    Activations Density 0.119%

    No Known Activations