© 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. 38329
    Prev
    Next
    INDEX
    Explanations

    headings and specific phrases

    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
     द्वारा
    -0.81
    retion
    -0.77
     diálogo
    -0.76
    泻
    -0.75
     dialogo
    -0.74
    chengla
    -0.74
    wska
    -0.73
    　　　　　　　
    -0.73
     یکی
    -0.71
    ικής
    -0.71
    POSITIVE LOGITS
    enfant
    0.82
    ﺟ
    0.81
    urfacing
    0.81
    gling
    0.81
     mensagens
    0.78
     부
    0.77
    Intercept
    0.77
    Insets
    0.74
     mouthful
    0.74
     obiekt
    0.74
    Activations Density 0.005%

    No Known Activations