© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5978
    Prev
    Next
    INDEX
    Explanations

    you can also

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

    The neuron fires on occurrences of the verb “choose,” especially in “choose from” option-listing contexts.

    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
     also
    0.68
     hart
    0.68
    ene
    0.67
    :
    0.67
    este
    0.66
    etary
    0.65
    也是
    0.65
    .
    0.64
     Also
    0.64
     für
    0.64
    POSITIVE LOGITS
     Apesar
    0.84
    vamo
    0.82
    ড্রিম
    0.80
    siz
    0.79
     flota
    0.78
     bookshelves
    0.75
    瑢
    0.75
     scones
    0.74
     Fleurit
    0.73
     Delegation
    0.73
    Activations Density 0.001%

    No Known Activations