© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9261
    Prev
    Next
    INDEX
    Explanations

    trained on massive dataset

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

    The neuron targets technical biochemical and physiological terms describing metabolic processes (e.g., breaking down, absorption, hormones, sugars, insulin, energy).

    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
     muß
    0.89
     ইংরাজ
    0.84
     لئے
    0.84
     skall
    0.83
     изпол
    0.82
     ইহাতে
    0.78
     hitherto
    0.77
    埸
    0.77
     বেশী
    0.74
     Presently
    0.73
    POSITIVE LOGITS
     —
    1.16
     —,
    1.09
     △
    1.09
     ✨
    1.08
     onboarding
    1.08
     badass
    1.07
     millennials
    1.04
     oftentimes
    1.02
     incentivize
    0.99
     يُ
    0.98
    Activations Density 0.200%

    No Known Activations