© 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. 116699
    Prev
    Next
    INDEX
    Explanations

    ID INT

    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
     comportamento
    -0.80
     actually
    -0.78
     --
    -0.75
    ——
    -0.74
    rag
    -0.73
    >}
    -0.72
    --
    -0.71
     impossibile
    -0.71
    ributions
    -0.71
     behaviors
    -0.71
    POSITIVE LOGITS
     voici
    0.75
    蚩
    0.75
    topus
    0.71
     Feliz
    0.71
     annonces
    0.70
     verbre
    0.69
     outings
    0.68
    ämpfer
    0.68
    Serviço
    0.68
     alér
    0.68
    Activations Density 0.017%

    No Known Activations