© 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. 100452
    Prev
    Next
    INDEX
    Explanations

    physical or conceptual spaces

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

    The neuron fires on words that reference metaphorical or conceptual “space” or “domain” (e.g. ground, territory, turf).

    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
    </td>
    -1.93
     daya
    -1.52
     preparados
    -1.52
     désolés
    -1.49
     fhall
    -1.44
    🩻
    -1.44
     évent
    -1.41
    bę
    -1.40
    ۹
    -1.40
    🌟
    -1.39
    POSITIVE LOGITS
     otra
    1.62
     какую
    1.57
     deline
    1.57
    corrhi
    1.55
     exuber
    1.55
    matology
    1.55
    ቼ
    1.55
    うーん
    1.53
    zzazione
    1.53
    </strong>
    1.51
    Activations Density 0.014%

    No Known Activations