© 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. 34561
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     évé
    -1.08
     volantes
    -0.96
     én
    -0.91
     libere
    -0.88
     roleId
    -0.86
     verdo
    -0.86
     fré
    -0.83
     vitale
    -0.82
     akár
    -0.82
     similaires
    -0.82
    POSITIVE LOGITS
     nachdem
    0.92
     kathol
    0.91
    之前的
    0.90
    малар
    0.88
    かせる
    0.86
     allAfrica
    0.83
    Mål
    0.83
     milliseconds
    0.82
    icto
    0.82
     wysokość
    0.82
    Activations Density 0.001%

    No Known Activations