© 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. 40069
    Prev
    Next
    INDEX
    Explanations

    call for details

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

    This neuron fires on title‐style or metadata tokens—section headings, numbered labels, and emphatic/exclamatory words in titles.

    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
     menyen
    -1.29
     hemd
    -1.28
     velg
    -1.21
    moderne
    -1.20
     jurk
    -1.19
    蕖
    -1.18
     schild
    -1.17
     plakat
    -1.15
     séries
    -1.15
     Meksi
    -1.15
    POSITIVE LOGITS
    <eos>
    1.48
     your
    1.40
     you
    1.35
    !
    1.27
     this
    1.27
    www
    1.24
    ......
    1.12
    !!!
    1.10
    ,”
    1.09
     return
    1.08
    Activations Density 0.003%

    No Known Activations