© 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. 8178
    Prev
    Next
    INDEX
    Explanations

    counts of things

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

    The neuron is looking for document‐metadata terms (e.g. dates, filing/posting references, tags, “filed on,” “posted on,” “concerning,” etc.).

    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
    terna
    0.86
    liğini
    0.82
    leri
    0.81
     compito
    0.81
     দায়িত্ব
    0.80
     দায়িত্ব
    0.79
    聸
    0.79
    খা
    0.79
    ovolta
    0.78
     使っ
    0.78
    POSITIVE LOGITS
     portions
    0.68
    טה
    0.68
    ಸ್ತ
    0.68
     nuggets
    0.68
     scrolls
    0.67
     seder
    0.66
     squirrels
    0.66
     cravings
    0.66
     vart
    0.66
    જબ
    0.65
    Activations Density 0.001%

    No Known Activations