© 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. 10-GEMMASCOPE-RES-131K
    7. 60601
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and comparisons

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

    The neuron primarily detects numeric literals with decimal points (i.e. floating-point numbers).

    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
     πριν
    -1.16
    Stadion
    -1.15
    tesi
    -1.10
    \
    -1.09
     ........
    -1.07
    our
    -1.05
    ischof
    -1.05
     nếu
    -1.05
     .......
    -1.04
    更多
    -1.03
    POSITIVE LOGITS
     not
    1.30
    Украина
    1.29
     äls
    1.16
     exquis
    1.08
    шь
    1.07
    真實
    1.05
    潁
    1.05
     consci
    1.05
    –
    1.05
    bandeja
    1.04
    Activations Density 0.045%

    No Known Activations