© 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. 38058
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

    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
    ПП
    -0.73
    Austria
    -0.73
     proche
    -0.73
    Full
    -0.73
     impresion
    -0.71
     प्रदेश
    -0.71
     apar
    -0.69
    ｧ
    -0.69
     OHIO
    -0.69
     विभ
    -0.69
    POSITIVE LOGITS
     doctorate
    0.80
    使其
    0.79
    thée
    0.77
     miliar
    0.75
    ֹ
    0.73
    feira
    0.73
    íž
    0.69
     ytterligare
    0.69
     memoized
    0.69
     sockaddr
    0.69
    Activations Density 0.036%

    No Known Activations