© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67329
    Prev
    Next
    INDEX
    Explanations

    coming out of

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

    The neuron activates on numeric expressions—digits, counts, ratios, and percentage‐style numbers 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_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
    for
    -2.39
    at
    -2.36
    _
    -2.30
    of
    -2.17
    as
    -2.16
     is
    -2.14
    u
    -2.08
    .
    -2.05
    you
    -2.02
    two
    -1.98
    POSITIVE LOGITS
    疴
    1.99
    ":[{
    1.95
     gadis
    1.88
    yeezy
    1.87
    酆
    1.86
    骘
    1.82
    𖥦
    1.82
    ᡵ
    1.81
    ⸒
    1.81
    
    1.80
    Activations Density 0.004%

    No Known Activations