© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6697
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on the word “mountain” (in any context or phrase).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    딘
    0.60
    otle
    0.57
    眾
    0.57
    zett
    0.56
    었다
    0.55
     कृपया
    0.55
    었던
    0.55
     Augusta
    0.54
     Boll
    0.54
     حدا
    0.54
    POSITIVE LOGITS
     nascetur
    0.64
    gomery
    0.61
    夆
    0.61
    ⛰
    0.60
     foothills
    0.60
    柰
    0.59
     biking
    0.56
    deer
    0.55
    Mont
    0.54
     c
    0.54
    Activations Density 0.168%

    No Known Activations