© 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. 494
    Prev
    Next
    INDEX
    Explanations

    metal 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
    ódnica
    -0.84
     Kollegen
    -0.77
    inx
    -0.71
    avimo
    -0.71
    corpion
    -0.71
     vocación
    -0.70
     потом
    -0.69
     Chasse
    -0.68
     protected
    -0.67
     rhyming
    -0.67
    POSITIVE LOGITS
    Band
    1.21
     Bandcamp
    1.12
     band
    1.04
    BAND
    0.98
     bands
    0.98
    band
    0.98
    Nuclear
    0.98
     BAND
    0.94
     Band
    0.90
     Bands
    0.90
    Activations Density 0.017%

    No Known Activations