© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82866
    Prev
    Next
    INDEX
    Explanations

    location and position

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

    This neuron activates strongly on words that refer to spatial placement or location (e.g., location, position, proximity, central, convenient).

    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
    dymo
    -0.83
    ɦ
    -0.82
    waypoints
    -0.79
     оружи
    -0.78
    hnout
    -0.77
    Clik
    -0.77
     AssemblyVersion
    -0.77
    obacterium
    -0.77
    Ход
    -0.76
     दर्ज
    -0.76
    POSITIVE LOGITS
     location
    8.00
     Location
    5.97
    location
    5.97
    Location
    5.91
     LOCATION
    5.25
     locations
    5.16
    LOCATION
    5.06
     ubicación
    4.53
    位置
    4.50
     위치
    4.16
    Activations Density 0.254%

    No Known Activations