© 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. 853
    Prev
    Next
    INDEX
    Explanations

    small

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

    The neuron activates on adjectives and phrases describing small, lightweight, or compact form factors.

    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
     WORDS
    0.69
     dirigeants
    0.68
     DIFFIC
    0.66
     BIRTH
    0.64
    ឬ
    0.63
     Fiziki
    0.62
     religiosos
    0.61
    橥
    0.61
     하나님의
    0.61
     BLOG
    0.61
    POSITIVE LOGITS
    ness
    0.75
    izable
    0.70
     but
    0.70
     and
    0.69
    izability
    0.69
     approach
    0.68
    ization
    0.66
     gọn
    0.66
    軽量
    0.65
    eness
    0.64
    Activations Density 0.001%

    No Known Activations