© 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. 7722
    Prev
    Next
    INDEX
    Explanations

    classes, numbers, or specific tokens

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

    The neuron is highly activated by floating‐point numerals (numbers containing a decimal point).

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

    the preposition "on" followed by a noun or noun phrase.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    language indicating motion, travel, or spatial transitions, especially expressed through movement-related verbs and prepositions.

    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
     মধুর
    0.84
     sombra
    0.82
    ạnh
    0.77
    arrivée
    0.74
    安全的
    0.73
     forthcoming
    0.73
     пользователя
    0.71
     चुप्पी
    0.69
    
    0.69
    Número
    0.68
    POSITIVE LOGITS
    j
    0.82
    itively
    0.80
    k
    0.80
    zigen
    0.73
     Calibri
    0.71
     whereupon
    0.71
     motorist
    0.71
    verlag
    0.71
     crafting
    0.70
    izion
    0.70
    Activations Density 0.000%

    No Known Activations