© 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. 28173
    Prev
    Next
    INDEX
    Explanations

    templates, parameters, page, nodes

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

    The neuron consistently lights up on content words that appear in section headings or titles—i.e. the key terms of questions, document headings, and bullet/list 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
    vän
    -1.22
     those
    -1.06
    crypted
    -1.05
    搅拌
    -1.02
    likation
    -1.01
    *************/
    -1.00
    荑
    -1.00
     dvě
    -1.00
     Rechten
    -1.00
     tatsächlich
    -0.99
    POSITIVE LOGITS
     you
    1.41
     in
    1.30
     will
    1.23
    }$.
    1.13
    एस
    1.09
     optionally
    1.09
     wyma
    1.09
     generated
    1.05
     may
    1.02
     appears
    1.02
    Activations Density 0.507%

    No Known Activations