© 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. 55701
    Prev
    Next
    INDEX
    Explanations

    this... is/leads/leaves

    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
    Ұ
    -0.91
     λε
    -0.90
    ществует
    -0.87
    vertebrates
    -0.87
     рассказ
    -0.81
     dzies
    -0.78
     kolik
    -0.78
    ઃ
    -0.77
     zelen
    -0.77
    fandom
    -0.77
    POSITIVE LOGITS
     brings
    4.41
     bring
    3.41
     leads
    2.91
    Bring
    2.73
     bringing
    2.67
     Bring
    2.66
    bring
    2.58
     Brings
    2.58
     Bringing
    2.17
     begs
    2.14
    Activations Density 0.043%

    No Known Activations