© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33633
    Prev
    Next
    INDEX
    Explanations

    directions and contrasts

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

    This neuron activates on words or fragments that denote directional axes or orientations (e.g., north/south/east/west or anatomical axes like anterio-posterior, mesial-distal, buccal-lingual).

    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
     francês
    -0.80
    ähkö
    -0.79
    ...-
    -0.77
    strophy
    -0.77
     BioLib
    -0.76
     minh
    -0.76
    .~
    -0.75
     diseñado
    -0.74
    ベージュ
    -0.73
     соревнования
    -0.73
    POSITIVE LOGITS
     versus
    0.99
     vs
    0.99
    ↔
    0.92
     VS
    0.91
     Versus
    0.88
     <=>
    0.87
     ↔
    0.86
    client
    0.85
    versus
    0.84
    posterior
    0.84
    Activations Density 0.096%

    No Known Activations