© 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. 34-GEMMASCOPE-RES-131K
    7. 99434
    Prev
    Next
    INDEX
    Explanations

    location and state of being

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

    The neuron activates on locative or positional cues—words and phrases (e.g. “where,” “located,” “is,” “are,” “wherever”) that indicate or ask about location.

    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
     fuera
    -0.88
    tura
    -0.86
    SO
    -0.86
     somewhere
    -0.85
     Tổng
    -0.84
    一直
    -0.84
     cementerio
    -0.83
    urals
    -0.83
    quête
    -0.82
     malattie
    -0.82
    POSITIVE LOGITS
     located
    2.66
    located
    1.80
    Located
    1.76
     Located
    1.72
     situated
    1.65
    位于
    1.36
     ubicado
    1.27
     ubicada
    1.25
     située
    1.16
     at
    1.15
    Activations Density 0.021%

    No Known Activations