© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32661
    Prev
    Next
    INDEX
    Explanations

    Avalanche, Vedran, KIIZ, Q

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find long runs of punctuation characters used as separators or divider lines.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    וּ
    -1.41
    \#:
    -1.18
    EdgeInsets
    -1.13
     silicone
    -1.13
    ִּ
    -1.10
     biografia
    -1.08
     ڤ
    -1.08
     jura
    -1.06
    וֹ
    -1.05
    lielmo
    -1.05
    POSITIVE LOGITS
     and
    1.21
     sorpresas
    1.15
    なんだけど
    1.15
     uñas
    1.14
    Instead
    1.14
    Etape
    1.13
    Ressources
    1.13
    leyball
    1.10
     parallèle
    1.09
     riego
    1.09
    Activations Density 0.000%

    No Known Activations