© 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. 10-GEMMASCOPE-RES-131K
    4. 69432
    Prev
    Next
    INDEX
    Explanations

    spatial relationships

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

    The neuron activates on words that indicate spatial relationships or proximity (e.g., “close to,” “halfway,” “between,” “across,” “opposite,” “near,” “next to”).

    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
     detecta
    -1.55
    tactez
    -1.49
     realmente
    -1.48
     distinta
    -1.45
     durumda
    -1.45
     наиболее
    -1.44
    tegen
    -1.39
     savvy
    -1.35
     sechs
    -1.35
     is
    -1.35
    POSITIVE LOGITS
    饪
    1.60
     '{{
    1.58
    If
    1.58
    は
    1.48
     pertanian
    1.46
    `{.
    1.42
     μὲν
    1.42
    );
    
    1.41
    ')"
    1.40
    ()?;
    1.40
    Activations Density 0.074%

    No Known Activations