© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1459
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on sensory perception verbs (e.g. look, taste, seem), i.e. language describing how something appears or is experienced.

    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
     nose
    0.55
     unable
    0.51
     mgr
    0.51
     visibility
    0.51
     сердца
    0.51
    を使用
    0.50
     נו
    0.50
     넘
    0.50
     வகைகள்
    0.50
     takip
    0.50
    POSITIVE LOGITS
     like
    2.09
    Like
    1.84
     Like
    1.82
    像是
    1.82
    like
    1.77
     LIKE
    1.76
    เหมือน
    1.64
     seperti
    1.63
     như
    1.55
     Seperti
    1.51
    Activations Density 0.607%

    No Known Activations