© 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. 22-GEMMASCOPE-RES-131K
    7. 13878
    Prev
    Next
    INDEX
    Explanations

    approximating quantities

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

    The neuron activates on numeric tokens, i.e. numbers and measurements 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_22/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
    を
    -2.13
    や
    -2.11
    และ
    -2.11
    そして
    -1.94
    と
    -1.94
    などを
    -1.91
    が
    -1.88
    も
    -1.85
    UCIÓN
    -1.76
    してました
    -1.75
    POSITIVE LOGITS
    ところに
    2.23
    為に
    2.16
    感じで
    2.08
     
    1.91
    en
    1.81
    ようです
    1.77
    つづく
    1.69
    ことも
    1.68
    y
    1.65
    "
    1.63
    Activations Density 0.021%

    No Known Activations