© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10698
    Prev
    Next
    INDEX
    Explanations

    left

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

    The neuron strongly activates on occurrences of the word “left” (in any capitalization or as part of a hyphenated token).

    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
    東北
    0.65
    东北
    0.59
    nT
    0.59
    ಪ್
    0.58
    ak
    0.56
     Tips
    0.55
     Troops
    0.55
    Ꮺ
    0.54
    carbons
    0.53
    šet
    0.53
    POSITIVE LOGITS
    側の
    0.92
    侧
    0.92
     side
    0.89
    边的
    0.89
     руку
    0.88
     sidebar
    0.88
     wing
    0.87
     flank
    0.87
    側
    0.87
    side
    0.82
    Activations Density 0.124%

    No Known Activations