© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 87089
    Prev
    Next
    INDEX
    Explanations

    finding things

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

    The neuron is activated by numeric tokens (integers or decimals), i.e. numbers and measurements.

    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
     both
    -1.35
     had
    -1.34
    。
    -1.33
     to
    -1.26
     for
    -1.25
     just
    -1.21
     which
    -1.20
    了不少
    -1.19
     especially
    -1.18
     what
    -1.17
    POSITIVE LOGITS
     recevrez
    1.43
     there
    1.36
    ⟷
    1.23
     favorita
    1.21
     немає
    1.20
     PRODUCTO
    1.17
    步伐
    1.16
    cuz
    1.16
     BRITAIN
    1.16
    headline
    1.15
    Activations Density 0.065%

    No Known Activations