© 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. 11117
    Prev
    Next
    INDEX
    Explanations

    difficult to

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

    The neuron fires on words expressing difficulty—e.g. “hard,” “difficult,” “gauge” in “hard to,” “difficult to,” 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
    挑战
    0.78
    adeus
    0.78
    挑戰
    0.75
    trek
    0.75
    ormous
    0.74
    zyme
    0.73
    Challenges
    0.71
    ’
    0.70
    challeng
    0.70
    创立
    0.70
    POSITIVE LOGITS
     souvenirs
    0.75
     complainant
    0.71
    ᇂ
    0.71
     any
    0.70
     shrines
    0.70
     shrine
    0.69
     unrecognizable
    0.67
     nikk
    0.67
     형식
    0.66
     напрямую
    0.66
    Activations Density 0.155%

    No Known Activations