© 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. 98114
    Prev
    Next
    INDEX
    Explanations

    DC voltage values

    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
    verez
    -0.77
    tuning
    -0.74
    لوك
    -0.72
    htiö
    -0.71
    waran
    -0.71
    toplankton
    -0.71
     length
    -0.69
    garan
    -0.69
     狼
    -0.68
    kreises
    -0.68
    POSITIVE LOGITS
     DC
    1.56
    DC
    1.28
     dc
    1.09
    dc
    1.05
     VDC
    1.03
    VDC
    0.86
    SDC
    0.85
     rectified
    0.84
    Twelve
    0.83
     volts
    0.82
    Activations Density 0.036%

    No Known Activations