© 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. 436
    Prev
    Next
    INDEX
    Explanations

    someone else

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

    The neuron fires strongly on words referring to people in general (e.g. everyone, anybody, someone, nobody).

    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
    -
    0.48
    に
    0.47
     показатели
    0.46
     función
    0.45
    에
    0.43
     появилась
    0.41
     функции
    0.41
     consecuencia
    0.41
     воздей
    0.41
    <0x80>
    0.40
    POSITIVE LOGITS
    知道
    0.48
    BusinessType
    0.45
    िकल
    0.43
     Coaches
    0.43
    圿
    0.43
    㣻
    0.43
    ಳೆದ
    0.42
     else
    0.41
    ंदरे
    0.40
     scolaire
    0.39
    Activations Density 0.264%

    No Known Activations