© 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. 15238
    Prev
    Next
    INDEX
    Explanations

    ,' => '

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

    The neuron flags most “content” tokens—i.e. non‐stopwords such as nouns, verbs, numbers, and punctuation—while ignoring very common function words.

    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
    .
    0.87
    2
    0.87
     which
    0.86
    0.84
    3
    0.84
    1
    0.81
    -
    0.80
      
    0.80
    {
    0.79
     facebook
    0.79
    POSITIVE LOGITS
    搛
    0.81
    ära
    0.78
    OAc
    0.75
    chnitten
    0.73
    䏲
    0.70
    庀
    0.68
    īd
    0.67
     చర్య
    0.66
    防疫
    0.66
    īn
    0.66
    Activations Density 43.344%

    No Known Activations