© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35281
    Prev
    Next
    INDEX
    Explanations

    guides, asks, modes, relates to

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

    The neuron fires on high-level document structure cues and metadata—section headings, labels, and navigational or “call-to-action” phrases (e.g. patent section titles, legal case headings, editorial notes, business listing prompts, etc.).

    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
     افرادی
    -1.63
     According
    -1.61
    สามารถ
    -1.61
     jotka
    -1.55
    According
    -1.52
    能够
    -1.51
    stånd
    -1.47
     ン
    -1.44
    较为
    -1.44
     Furthermore
    -1.39
    POSITIVE LOGITS
     again
    1.63
    直至
    1.58
     to
    1.56
     viernes
    1.48
     ebenso
    1.44
    selas
    1.44
     біль
    1.41
     incluye
    1.41
    特に
    1.33
     plus
    1.31
    Activations Density 0.662%

    No Known Activations