© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57246
    Prev
    Next
    INDEX
    Explanations

    UNESCO Biosphere Reserve, Alpine Towns communės

    np_acts-logits-general · gemini-2.5-flash-lite

    geographic administrative divisions like cantons, counties, regions, and districts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Regions
    -0.94
    REGION
    -0.88
     INDEX
    -0.83
     Municipality
    -0.81
    Regions
    -0.81
    regions
    -0.78
     municipality
    -0.77
     Region
    -0.76
     regions
    -0.75
    Region
    -0.74
    POSITIVE LOGITS
     chaves
    0.75
    ⁸
    0.75
    bul
    0.73
    Schemes
    0.73
    scheme
    0.72
     llave
    0.71
     kommunizieren
    0.69
     orbit
    0.68
     cheese
    0.68
     Pius
    0.68
    Activations Density 0.046%

    No Known Activations