© 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. 2417
    Prev
    Next
    INDEX
    Explanations

    Bing Image Creator

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

    The neuron fires on proper brand or product names (especially website/service names).

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

    proper nouns, specifically brand names and product names (especially software/technology products and services).

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

    names of specific brands, apps, and online services (proper-noun product/company names).

    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
     chlorides
    0.48
    攷
    0.48
     ketones
    0.46
     물질
    0.45
     kidneys
    0.45
     triglycerides
    0.45
    TextureData
    0.45
     homologous
    0.44
     halides
    0.44
     fluttering
    0.44
    POSITIVE LOGITS
    ®
    0.66
    ’
    0.60
    ®.
    0.60
    '
    0.58
    Ⓡ
    0.58
    ®,
    0.55
    などに
    0.55
    에서
    0.55
    ův
    0.55
     στην
    0.54
    Activations Density 0.000%

    No Known Activations