© 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. 83054
    Prev
    Next
    INDEX
    Explanations

    ` line or number suffixes

    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
     carrot
    -0.79
     entendu
    -0.77
    Campbell
    -0.74
     מוע
    -0.74
     BASIC
    -0.73
    ByteString
    -0.72
    gü
    -0.72
     Sultan
    -0.71
     обращения
    -0.71
    弉
    -0.71
    POSITIVE LOGITS
     frühen
    0.67
    ivoli
    0.63
    рис
    0.63
     ubica
    0.63
     intent
    0.62
    feliz
    0.61
     Även
    0.61
    𝑤
    0.60
     sprá
    0.59
     Within
    0.59
    Activations Density 0.084%

    No Known Activations