© 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. 73907
    Prev
    Next
    INDEX
    Explanations

    marketing, department, Wolverine, Heat, Fonts

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

    This neuron fires on structural or formatting tokens that mark section headings, lists, or separators (e.g. heading keywords, list‐marker brackets, bullets, and line‐divider symbols).

    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
     Dinas
    -1.22
     vingt
    -1.12
    がとても
    -1.08
    を使用して
    -1.07
     erhi
    -1.07
     solch
    -1.05
    めちゃくちゃ
    -1.05
     interrom
    -1.05
    驁
    -1.03
     magnific
    -1.02
    POSITIVE LOGITS
     all
    1.32
     an
    1.30
     that
    1.28
    Ḥ
    1.26
     with
    1.24
     Non
    1.22
     one
    1.20
     as
    1.17
     ((
    1.14
     which
    1.13
    Activations Density 0.011%

    No Known Activations