© 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. 75835
    Prev
    Next
    INDEX
    Explanations

    river mouth or opening

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

    This neuron detects words used in geographic-location descriptions—terms that mark where places or features are situated (e.g., “located,” “situated,” “at,” “mouth,” names of rivers).

    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
    ตร
    -0.73
    nail
    -0.71
     sidebar
    -0.69
     Nuss
    -0.66
    onga
    -0.66
    oles
    -0.66
     Miriam
    -0.66
    isku
    -0.65
     odyssey
    -0.64
     Footnote
    -0.64
    POSITIVE LOGITS
     mouth
    3.92
     mouths
    2.97
    mouth
    2.97
     Mouth
    2.75
    Mouth
    2.70
    MOUTH
    2.25
    口
    2.19
     entrance
    2.09
    ปาก
    2.03
     opening
    1.80
    Activations Density 0.062%

    No Known Activations