© 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. 78316
    Prev
    Next
    INDEX
    Explanations

    Montreal, Canada, sports

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

    the names of specific real-world entities (especially place names, institutions, and other proper nouns).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    象
    -0.78
    ложении
    -0.76
    ntilde
    -0.74
    🇫
    -0.73
    veil
    -0.73
    pfn
    -0.69
     Tacoma
    -0.69
     france
    -0.69
     Vallejo
    -0.68
    髦
    -0.66
    POSITIVE LOGITS
     Montreal
    1.40
    Montreal
    1.30
     McGill
    1.19
     Concordia
    0.94
     Montréal
    0.83
    促進
    0.79
    sibili
    0.76
    痴
    0.74
    品種
    0.73
    Lach
    0.71
    Activations Density 0.041%

    No Known Activations