© 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. 10-GEMMASCOPE-RES-131K
    7. 60358
    Prev
    Next
    INDEX
    Explanations

    citation and academic references

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

    The neuron fires on numeric references and identifiers—i.e. tokens representing numbers (years, section / figure numbers, citation indices, 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_10/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
     in
    -3.25
     (
    -2.66
     egenskaper
    -2.20
    着脸
    -2.17
     egens
    -2.13
     virke
    -2.02
     on
    -1.92
    ∅
    -1.85
    şek
    -1.85
    elsif
    -1.83
    POSITIVE LOGITS
     and
    4.00
    了一些
    2.88
    了自己
    2.45
    了些
    2.44
    了不少
    2.42
     (!__
    2.36
    6
    2.31
    5
    2.28
     taşlı
    2.23
    了很多
    2.22
    Activations Density 32.894%

    No Known Activations