© 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. 22-GEMMASCOPE-RES-131K
    7. 65651
    Prev
    Next
    INDEX
    Explanations

    place names and locations

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

    The neuron detects geographic place names (e.g. towns, streets, neighborhoods, parks, lakes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    つづく
    -1.72
    ほら
    -1.66
    んでしょう
    -1.61
    感じが
    -1.58
    為に
    -1.57
    ＊＊＊
    -1.54
    んだよね
    -1.52
    本当の
    -1.45
    ＊＊＊＊
    -1.45
    んですけど
    -1.45
    POSITIVE LOGITS
    や
    1.38
    inches
    1.22
    そして
    1.21
     
    1.19
    ds
    1.18
    1.18
    i
    1.14
     mentre
    1.13
    Si
    1.12
    と
    1.12
    Activations Density 0.059%

    No Known Activations