© 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. 22-GEMMASCOPE-RES-131K
    7. 130400
    Prev
    Next
    INDEX
    Explanations

    . followed by word

    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_22/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
     unicorn
    -0.81
    versible
    -0.77
    ƺ
    -0.76
    BeginInit
    -0.75
    まずは
    -0.75
     ağır
    -0.75
     Flushing
    -0.75
    Coppa
    -0.75
    ophora
    -0.73
    чиком
    -0.73
    POSITIVE LOGITS
     hadn
    0.90
     movimentos
    0.89
    に戻
    0.86
    cisive
    0.84
     itself
    0.84
    umerable
    0.82
    induced
    0.79
     another
    0.78
     costumbre
    0.77
    quate
    0.77
    Activations Density 0.011%

    No Known Activations