© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35638
    Prev
    Next
    INDEX
    Explanations

    titles of articles or books

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

    The neuron selectively activates on segments of formal titles or headings of works (e.g. book, article, or film titles).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     prochaines
    -1.09
     қара
    -1.09
    為に
    -1.07
    zaak
    -1.06
     difficultés
    -1.05
     pertes
    -1.03
     pourraient
    -1.02
    跻
    -1.02
    ikin
    -1.02
     "~
    -1.02
    POSITIVE LOGITS
     on
    1.41
     about
    1.37
     in
    1.36
     article
    1.34
     just
    1.23
    〈
    1.20
     yPos
    1.13
     so
    1.13
     Conclusion
    1.13
     how
    1.12
    Activations Density 0.015%

    No Known Activations