© 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. 65487
    Prev
    Next
    INDEX
    Explanations

    measuring and quantifiable results

    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
    億円
    -0.76
    <0xAB>
    -0.75
    läufe
    -0.74
    ético
    -0.71
    MCA
    -0.71
    šla
    -0.71
     Nj
    -0.70
     Littleton
    -0.69
    пите
    -0.69
    ionalmente
    -0.68
    POSITIVE LOGITS
     measurement
    6.34
     measurements
    6.34
     measuring
    6.03
     measured
    5.94
     measure
    5.69
    Measurement
    5.16
     Measurement
    5.13
     Measurements
    5.09
    measurement
    5.00
    measure
    4.91
    Activations Density 0.343%

    No Known Activations