© 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. 113071
    Prev
    Next
    INDEX
    Explanations

    place names and associated locations

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

    The neuron strongly activates on capitalized place names (cities, regions, counties, etc.), so it’s detecting geographic location mentions.

    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
    鉏
    -1.59
    ativement
    -1.59
    ޗ
    -1.55
    __':
    -1.51
     renfor
    -1.49
    haviours
    -1.48
    €”
    -1.48
    lowed
    -1.46
    helpful
    -1.42
    cended
    -1.41
    POSITIVE LOGITS
    .”
    1.62
     inneren
    1.48
     eigentlichen
    1.43
     don
    1.36
    雋
    1.33
     strive
    1.29
     offenen
    1.28
    ↵↵
    1.26
     createSlice
    1.25
     Spra
    1.22
    Activations Density 0.158%

    No Known Activations