© 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. 40150
    Prev
    Next
    INDEX
    Explanations

    distance or spacing between things

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

    This neuron detects words that describe spatial arrangement or proximity (e.g., spacing, closer, together, spaced).

    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
     it
    -1.26
     momentos
    -1.26
     things
    -1.25
     capas
    -1.23
    เกง
    -1.19
    поді
    -1.19
     zlo
    -1.18
    СЯ
    -1.17
     autorisation
    -1.17
    ggg
    -1.16
    POSITIVE LOGITS
     où
    1.37
    ();*/
    1.34
     your
    1.29
     defends
    1.29
    ();//
    1.27
    between
    1.27
     between
    1.27
    ());//
    1.23
     Cię
    1.23
     które
    1.19
    Activations Density 0.058%

    No Known Activations