© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3563
    Prev
    Next
    INDEX
    Explanations

    dive into

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

    The neuron strongly activates on common base‐form action verbs (e.g. run, get, dig, lean) that denote dynamic events or movements.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    飄
    0.46
     europäischen
    0.46
     dirección
    0.46
    hton
    0.45
     совета
    0.44
    öffnung
    0.43
     Perspectives
    0.43
    飘
    0.43
    𝗽
    0.42
     keram
    0.42
    POSITIVE LOGITS
     quantitatively
    0.48
    不仅仅
    0.48
    不仅
    0.48
    也很
    0.47
     використання
    0.47
    亗
    0.46
    绞
    0.45
    จากการ
    0.45
     ayrıca
    0.45
    وک
    0.44
    Activations Density 0.268%

    No Known Activations