© 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. 10-GEMMASCOPE-RES-131K
    7. 66357
    Prev
    Next
    INDEX
    Explanations

    place names

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

    This neuron detects mentions of geographic place names (cities, towns, or counties).

    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
    CurtirCurtir
    -2.81
    躂
    -2.47
     parlato
    -2.33
     概要
    -2.31
     Roughly
    -2.22
    裥
    -2.20
     Belakang
    -2.20
     ricevuto
    -2.17
     Immediately
    -2.17
     chiesto
    -2.16
    POSITIVE LOGITS
    all
    2.17
     =
    2.16
    or
    2.09
    at
    1.98
    de
    1.95
    <
    1.94
    no
    1.94
     -
    1.84
    <i>
    1.81
    from
    1.81
    Activations Density 0.012%

    No Known Activations