© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32703
    Prev
    Next
    INDEX
    Explanations

    words starting with pron

    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
    āli
    -0.80
     Voz
    -0.74
    лось
    -0.73
    WireFormat
    -0.73
    katkan
    -0.71
     procès
    -0.69
     employee
    -0.69
     immobilier
    -0.68
     Wal
    -0.68
    hod
    -0.68
    POSITIVE LOGITS
     Pron
    1.29
    Pron
    1.23
     pron
    1.20
    pron
    1.13
    想知道
    0.84
    FC
    0.81
    <h6>
    0.80
    戦
    0.77
    ciation
    0.77
     betal
    0.75
    Activations Density 0.018%

    No Known Activations