© 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. 10-GEMMASCOPE-RES-131K
    7. 45725
    Prev
    Next
    INDEX
    Explanations

    NOT FINAL UNTIL

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

    The neuron specifically fires on the uppercase token “FINAL,” flagging occurrences of that word in the text.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dát
    -1.20
    führen
    -1.13
     különböz
    -1.09
    那些
    -1.09
     Umständen
    -1.08
    AMOR
    -1.06
     tidligere
    -1.06
     vlastnosti
    -1.05
     ausgestattet
    -1.04
    ではなく
    -1.03
    POSITIVE LOGITS
     still
    1.54
     when
    1.53
     there
    1.40
     though
    1.23
    </b>
    1.20
     chapa
    1.17
    も良い
    1.16
     batata
    1.15
     it
    1.13
     midway
    1.12
    Activations Density 0.032%

    No Known Activations