© 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. 22230
    Prev
    Next
    INDEX
    Explanations

    small towns and villages

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

    The neuron fires on mentions of towns—especially the phrase “small town” or similar town descriptors.

    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
    ครื่อง
    -1.78
     désactiv
    -1.77
     récemment
    -1.73
    鯷
    -1.70
    鹩
    -1.63
    噐
    -1.62
     eſſ
    -1.62
    ACIÓN
    -1.60
    谂
    -1.60
    橚
    -1.59
    POSITIVE LOGITS
     are
    1.99
    :
    1.91
    )
    1.81
    -
    1.68
    (
    1.61
    l
    1.61
    d
    1.55
     town
    1.47
    ."
    1.47
    },
    1.47
    Activations Density 0.044%

    No Known Activations