© 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. 8652
    Prev
    Next
    INDEX
    Explanations

    US, Canada, UK availability

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

    The neuron fires most strongly on infrequent, content‐bearing “keyword” tokens (e.g. summary, accuracy, data, printed, please), i.e. terms with high information value.

    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
     streetwear
    0.30
    乎
    0.30
     omnichannel
    0.30
     countertops
    0.29
     tặng
    0.27
     TikTok
    0.26
     Loft
    0.26
     creatives
    0.26
     reimag
    0.26
    ılım
    0.26
    POSITIVE LOGITS
     সুতরাং
    0.28
     તેથી
    0.28
    😰
    0.28
     Sedangkan
    0.28
    currentSprite
    0.28
    やや
    0.27
    Cannot
    0.27
    Bubble
    0.27
    ListBox
    0.27
    SessionFactory
    0.27
    Activations Density 0.000%

    No Known Activations