© 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. 622
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on words that denote analytical or evaluation actions (e.g. assess, evaluate, quantify, unpack).

    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
    1
    0.60
     menulis
    0.60
    3
    0.59
     schrieb
    0.57
    2
    0.56
     gibt
    0.54
     nennt
    0.54
     pergi
    0.53
    6
    0.51
     benutzt
    0.51
    POSITIVE LOGITS
    如何在
    0.59
     socioeconomic
    0.59
    如何
    0.58
     tradeoffs
    0.57
    どのように
    0.57
     sociocultural
    0.56
    interactions
    0.55
    cómo
    0.55
    是否有
    0.55
     pathologies
    0.54
    Activations Density 0.000%

    No Known Activations