© 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. 22-GEMMASCOPE-RES-131K
    7. 73413
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    The neuron activates on numeric tokens—integers and decimals—highlighting any numbers or 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
     and
    -1.15
    wieś
    -1.14
     it
    -1.12
    ᴢ
    -1.08
     permiti
    -1.08
    sonance
    -1.02
     frasco
    -1.02
    lıkla
    -1.02
     begrij
    -1.01
    に行った
    -1.00
    POSITIVE LOGITS
     is
    1.03
     ケーブル
    1.02
    These
    0.99
    The
    0.96
     примерно
    0.95
     meistens
    0.95
     egenskaper
    0.93
     acrob
    0.93
     Bjør
    0.93
    They
    0.91
    Activations Density 0.243%

    No Known Activations