© 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. 10-GEMMASCOPE-RES-131K
    7. 84678
    Prev
    Next
    INDEX
    Explanations

    Albany, New York

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

    The neuron detects mentions of “Albany.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    archiwizowane
    -3.83
    '
    -3.02
     are
    -2.98
     dando
    -2.86
     eigentliche
    -2.84
     genaue
    -2.81
     gesamte
    -2.78
     reconoc
    -2.77
    if
    -2.75
     diversos
    -2.75
    POSITIVE LOGITS
    𓆜
    3.30
     supremely
    3.17
     unrelenting
    3.14
     unusually
    2.98
    執筆
    2.92
     lavish
    2.89
     weirdly
    2.81
     blatantly
    2.81
     radically
    2.77
     poignant
    2.72
    Activations Density 0.001%

    No Known Activations