© 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. 32855
    Prev
    Next
    INDEX
    Explanations

    license text fragments

    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
    kuuta
    -0.69
    架
    -0.67
     xuất
    -0.66
    uom
    -0.66
    𝗺
    -0.64
     vícti
    -0.63
    脐
    -0.63
    präche
    -0.63
     tapi
    -0.62
    lusconi
    -0.62
    POSITIVE LOGITS
     tunnel
    0.71
     freezing
    0.71
    unanje
    0.68
    tunnel
    0.68
     tunnels
    0.67
    {\"
    0.67
    生產
    0.66
     przeds
    0.66
    ●●
    0.66
    cdn
    0.65
    Activations Density 0.057%

    No Known Activations