© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116472
    Prev
    Next
    INDEX
    Explanations

    country code domains in URLs

    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
    ながら
    -0.73
    SM
    -0.73
     τὸν
    -0.72
    &
    -0.71
     such
    -0.71
    HS
    -0.71
     have
    -0.71
    j
    -0.71
    SL
    -0.70
    S
    -0.70
    POSITIVE LOGITS
    λης
    1.00
    /?
    1.00
    Alamat
    0.98
     domain
    0.97
    groep
    0.97
    DOMAIN
    0.96
    /)
    0.96
     odası
    0.94
     domains
    0.93
     lanzar
    0.93
    Activations Density 0.028%

    No Known Activations