© 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. 13988
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on runs of punctuation or formatting “tokens” (especially multi‐dot ellipses and similar repeated symbols), i.e. non-word separator sequences.

    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
     Webber
    0.57
     reglamento
    0.57
    },{"
    0.55
    स्थल
    0.54
    перы
    0.53
     esconder
    0.53
    द्रोह
    0.52
     Braunschweig
    0.52
    jPanel
    0.52
     Schön
    0.52
    POSITIVE LOGITS
     。
    0.54
    bli
    0.52
    。\
    0.52
    icip
    0.51
     devi
    0.51
     importa
    0.51
    ikation
    0.51
    hc
    0.49
    ıntı
    0.49
     ፣
    0.49
    Activations Density 0.036%

    No Known Activations