© 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. 22-GEMMASCOPE-RES-131K
    7. 14561
    Prev
    Next
    INDEX
    Explanations

    Virginia on, This cheese, Q: math, 200

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

    The neuron fires on tokens that are purely numerical (digit sequences), i.e. it detects numbers in code/XML.

    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
     Ellos
    -1.22
    chodzą
    -1.18
    ympto
    -1.17
     Seorang
    -1.14
     Temos
    -1.13
    ковского
    -1.13
     Tienen
    -1.09
    gears
    -1.09
     Schülern
    -1.09
     Mereka
    -1.08
    POSITIVE LOGITS
     applicable
    1.20
    parametrize
    1.15
    烘焙
    1.13
    oun
    1.13
     menetap
    1.11
    orm
    1.10
     художник
    1.09
    +}$
    1.09
    or
    1.09
    <th>
    1.09
    Activations Density 0.009%

    No Known Activations