© 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. 34-GEMMASCOPE-RES-131K
    7. 58396
    Prev
    Next
    INDEX
    Explanations

    place or position within

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

    The neuron fires on words that denote location or position (e.g. “place,” “residing,” “in”).

    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
    indle
    -0.89
     traseiro
    -0.85
    ixer
    -0.81
     partiellement
    -0.80
     tisch
    -0.78
     deswegen
    -0.78
     largement
    -0.77
    懨
    -0.76
     entièrement
    -0.74
     Schach
    -0.73
    POSITIVE LOGITS
     on
    1.43
     in
    1.43
     reserved
    1.37
     alongside
    1.29
     among
    1.25
     vacated
    1.09
     within
    1.06
    reserved
    1.05
     amongst
    1.00
     Among
    0.99
    Activations Density 0.030%

    No Known Activations