© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79908
    Prev
    Next
    INDEX
    Explanations

    HTML entities or quotation marks

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

    The neuron fires on section headings or table‐of‐contents entries in a document, especially the “Summary” heading.

    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
     to
    -1.45
     Despite
    -1.19
     on
    -1.19
     despite
    -1.16
     after
    -1.16
     After
    -1.09
     reinforces
    -1.09
     by
    -1.09
     in
    -1.09
    しますね
    -1.09
    POSITIVE LOGITS
    すっ
    1.18
    に入れる
    1.16
     protože
    1.13
    looks
    1.10
     grandiose
    1.10
     zowel
    1.09
     Dinas
    1.06
    zhen
    1.06
    gonna
    1.05
    rsquo
    1.05
    Activations Density 0.051%

    No Known Activations