© 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. 86790
    Prev
    Next
    INDEX
    Explanations

    ol breadcrumb

    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
    més
    -0.87
    tente
    -0.86
    𝖚
    -0.84
    férés
    -0.81
    verson
    -0.79
    ётся
    -0.79
    goon
    -0.79
    eluarkan
    -0.78
     leitor
    -0.78
     asumir
    -0.77
    POSITIVE LOGITS
    breadcrumb
    1.05
     bread
    0.93
    ol
    0.87
    Breadcrumb
    0.84
     Bread
    0.84
     rewind
    0.78
    breadcrumbs
    0.75
     breadcrumbs
    0.74
     olmayan
    0.73
    バーガー
    0.72
    Activations Density 0.008%

    No Known Activations