© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48146
    Prev
    Next
    INDEX
    Explanations

    generic collections

    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
    OLOGÍA
    -0.88
    нению
    -0.84
    itten
    -0.80
     bahan
    -0.79
     wł
    -0.79
    icer
    -0.79
    וץ
    -0.78
    icat
    -0.78
     FABRIC
    -0.78
    ご了承
    -0.77
    POSITIVE LOGITS
     Fet
    0.79
     GY
    0.79
     tapas
    0.79
     __________
    0.77
    онер
    0.76
    Generic
    0.75
     hairline
    0.74
     FET
    0.74
    genic
    0.73
     wou
    0.71
    Activations Density 0.007%

    No Known Activations