© 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. 99919
    Prev
    Next
    INDEX
    Explanations

    place names ending in ans

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

    The neuron fires strongly on the letter sequence “ans” wherever it appears inside words.

    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
     Bent
    -0.77
    וכר
    -0.76
     possible
    -0.75
    Gig
    -0.71
     Vang
    -0.71
     informal
    -0.70
    楕
    -0.70
    али
    -0.70
    遊び
    -0.70
     faith
    -0.69
    POSITIVE LOGITS
    hens
    0.83
    şi
    0.77
    ")}
    0.75
    larna
    0.74
    ız
    0.73
    yyah
    0.73
    araman
    0.72
     Septembre
    0.72
     miejsce
    0.69
    :";
    0.68
    Activations Density 0.034%

    No Known Activations