© 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. 3363
    Prev
    Next
    INDEX
    Explanations

    statistics

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

    The neuron fires strongly on numeric year mentions (four‐digit dates).

    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
    വിന്
    0.89
     azide
    0.83
    𒌑
    0.82
    ným
    0.80
    ర్ణ
    0.80
     applique
    0.79
     ਯ
    0.79
    prize
    0.78
     komponent
    0.78
     nồi
    0.78
    POSITIVE LOGITS
     《
    0.68
    Card
    0.66
    BlackRatingDiff
    0.66
     Брита
    0.65
    、《
    0.63
    Alta
    0.63
     Lle
    0.61
     Correspondent
    0.60
    Businesses
    0.60
    Makanan
    0.60
    Activations Density 0.000%

    No Known Activations