© 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. 66182
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    âteaux
    -0.97
    ㄑ
    -0.93
    ânico
    -0.90
    ày
    -0.88
     Agua
    -0.87
    capsulation
    -0.86
     consom
    -0.85
     Oats
    -0.85
     Ricci
    -0.85
     aanbod
    -0.85
    POSITIVE LOGITS
     if
    1.10
     Их
    1.07
    零
    0.90
     val
    0.90
     by
    0.90
     minus
    0.90
    IN
    0.88
     Z
    0.88
    хло
    0.87
     of
    0.86
    Activations Density 0.076%

    No Known Activations