© 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. 81487
    Prev
    Next
    INDEX
    Explanations

    sports team abbreviations and records

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

    The neuron strongly activates on numeric tokens (digits or numbers), effectively detecting numbers and numeric sequences in the text.

    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
     for
    -1.45
     a
    -1.36
     this
    -1.31
     that
    -1.27
     an
    -1.24
     which
    -1.18
     just
    -1.16
     create
    -1.14
     with
    -1.12
     by
    -1.10
    POSITIVE LOGITS
     vs
    1.30
    riert
    1.18
     déta
    1.14
    ް
    1.13
     entraî
    1.13
     ถ้า
    1.12
     indust
    1.11
     vazio
    1.08
     évidemment
    1.08
     图库
    1.08
    Activations Density 0.034%

    No Known Activations