© 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. 77319
    Prev
    Next
    INDEX
    Explanations

    Canary, Canarian, Canary Islands

    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
    Fácil
    -0.71
    icksburg
    -0.70
    shut
    -0.70
    río
    -0.69
    िर
    -0.69
     updating
    -0.69
     pubblic
    -0.69
     mexicano
    -0.68
     khớp
    -0.67
    ⛩
    -0.67
    POSITIVE LOGITS
     Canary
    1.67
     Tenerife
    1.53
     volcanic
    1.23
     canary
    1.16
    カナ
    1.16
     Lanzarote
    1.13
    Tener
    1.12
     Volcanic
    1.08
     volcano
    1.06
     island
    1.02
    Activations Density 0.016%

    No Known Activations