© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11819
    Prev
    Next
    INDEX
    Explanations

    lunar lactation

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

    The neuron is selectively activating on numeric tokens (especially measurements, quantities, or decimal‐formatted values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    named entities—especially capitalized proper nouns, acronyms, and alphanumeric model codes or technical specifications.

    oai_token-act-pair · gpt-5Triggered 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
    citizens
    0.70
    keny
    0.68
     яких
    0.66
    purch
    0.64
     नागरिकों
    0.64
    🏢
    0.64
    idik
    0.63
    exempt
    0.63
    無料で
    0.63
    コンピュータ
    0.63
    POSITIVE LOGITS
     Reversed
    0.74
    }}^{-
    0.73
     reverse
    0.67
    ,
    0.65
     Noting
    0.63
     reversed
    0.61
     Reverse
    0.61
     reversals
    0.61
     reverses
    0.59
     Gün
    0.58
    Activations Density 1.093%

    No Known Activations