© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2659
    Prev
    Next
    INDEX
    Explanations

    X vs Y comparisons

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

    The neuron activates on occurrences of the abbreviation “vs” (versus) used for comparisons or matchups.

    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_24_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
    नस
    0.52
    czne
    0.51
     Ayn
    0.51
    both
    0.50
     fromi
    0.50
    bD
    0.50
    _='
    0.50
    bP
    0.50
    urnd
    0.49
     Veron
    0.49
    POSITIVE LOGITS
    ité
    0.55
     ಆಗಿದೆ
    0.54
    stück
    0.53
    Angleterre
    0.52
    ία
    0.52
    ות
    0.52
    ယ်
    0.52
     इंग्लंड
    0.50
     is
    0.50
    തന്ത്ര
    0.49
    Activations Density 0.085%

    No Known Activations