© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34151
    Prev
    Next
    INDEX
    Explanations

    technical documentation and guides

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

    The neuron strongly activates on documentation‐style headings and keywords (e.g. “Overview,” “Documentation,” section titles, and similar link or menu labels).

    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
     a
    -1.23
     ингреди
    -1.20
     last
    -1.18
     với
    -1.10
     similar
    -1.06
     such
    -1.05
     витами
    -1.05
    過去の
    -1.05
     yesterday
    -1.05
     then
    -1.05
    POSITIVE LOGITS
    וּ
    1.57
     ſu
    1.48
    cillary
    1.43
    рѣ
    1.33
     utilisateur
    1.30
     ſer
    1.28
    消失了
    1.27
    וֹ
    1.25
     triomphe
    1.23
     TÉ
    1.22
    Activations Density 0.069%

    No Known Activations