© 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. 34-GEMMASCOPE-RES-131K
    7. 75979
    Prev
    Next
    INDEX
    Explanations

    list item separators

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

    The neuron flags numeric literals (tokens composed of digits) wherever they appear.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     REALLY
    -1.25
     its
    -1.23
     SECOND
    -1.22
    actually
    -1.20
     ランプ
    -1.13
     TÉ
    -1.12
     kompati
    -1.10
    
    -1.10
     MÁ
    -1.09
     ピンク
    -1.09
    POSITIVE LOGITS
     &
    1.33
    そして
    1.31
     and
    1.28
     their
    1.27
     or
    1.16
     now
    1.15
     sometimes
    1.14
     etc
    1.09
     possibly
    1.09
     can
    1.08
    Activations Density 0.096%

    No Known Activations