© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6701
    Prev
    Next
    INDEX
    Explanations

    religion and society fears

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

    This neuron fires on verbs and auxiliaries that express speech acts, statements, demands, or intentions—especially modal verbs like “will”/“would” and reporting verbs such as “said,” “asked,” “claimed,” “demanded,” 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_31_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
     কর্তৃপক্ষের
    0.71
     কর্তৃপক্ষ
    0.66
     വിശദ
    0.64
     विनियमन
    0.64
     করবার
    0.63
     السيد
    0.63
    かなり
    0.62
    லான
    0.60
     sekitar
    0.60
    とりあえず
    0.60
    POSITIVE LOGITS
     आतंकवाद
    0.68
     conspiracies
    0.67
     विनाश
    0.63
     evil
    0.61
     sheath
    0.61
     dreaming
    0.61
     coward
    0.61
    evil
    0.61
    killer
    0.61
     mentality
    0.60
    Activations Density 0.111%

    No Known Activations