© 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. 22-GEMMASCOPE-RES-131K
    7. 130673
    Prev
    Next
    INDEX
    Explanations

    ob/ff start of text

    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
     disiplin
    -1.88
    ・・・」
    -1.84
     hunde
    -1.83
     kafe
    -1.73
     ekst
    -1.71
     berge
    -1.65
     kaos
    -1.62
     Luar
    -1.60
     Gemeinsame
    -1.60
     fald
    -1.59
    POSITIVE LOGITS
    (+
    1.73
     \
    1.67
    \
    1.64
     atractiva
    1.61
     duradero
    1.60
    <em>
    1.59
     protože
    1.59
    *
    1.55
    -\\
    1.55
     "
    1.55
    Activations Density 0.000%

    No Known Activations