© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48157
    Prev
    Next
    INDEX
    Explanations

    unit, units, unidad, ユニット

    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
    InBytes
    -0.73
     пона
    -0.72
     marcher
    -0.70
    ρεύ
    -0.68
     injec
    -0.66
     mvc
    -0.66
    writerow
    -0.66
    window
    -0.65
     verhindert
    -0.64
    inner
    -0.63
    POSITIVE LOGITS
     unit
    1.96
     Unit
    1.76
    Unit
    1.69
     UNIT
    1.59
    unit
    1.53
     units
    1.46
    UNIT
    1.41
    ユニット
    1.35
     Units
    1.30
     unidad
    1.27
    Activations Density 0.010%

    No Known Activations