© 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. 34-GEMMASCOPE-RES-131K
    7. 76823
    Prev
    Next
    INDEX
    Explanations

    average or mean values

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

    The neuron activates on numeric tokens, especially multi‐digit figures like years, measurements, or statistical values.

    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
    mands
    -1.54
    several
    -1.50
    olving
    -1.38
     CERTAIN
    -1.38
    mme
    -1.38
    possibly
    -1.36
    athers
    -1.35
     diversos
    -1.34
     enorme
    -1.34
    obviously
    -1.34
    POSITIVE LOGITS
     for
    2.11
     time
    1.74
     before
    1.55
     amount
    1.55
     had
    1.43
     began
    1.40
     gets
    1.38
     first
    1.32
     after
    1.31
     took
    1.31
    Activations Density 0.050%

    No Known Activations