© 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. 34-GEMMASCOPE-RES-131K
    7. 99144
    Prev
    Next
    INDEX
    Explanations

    numbers and ordinals

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

    This neuron detects hexadecimal color codes (e.g. the “#f2f2f2” in HTML‐style attributes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    дование
    -0.90
    ⑪
    -0.88
     another
    -0.86
     первого
    -0.85
     prakti
    -0.85
    autre
    -0.85
    ୧
    -0.85
    aluz
    -0.85
     viso
    -0.84
     indirizzo
    -0.83
    POSITIVE LOGITS
    3
    1.70
     third
    1.45
     Thirdly
    1.21
    ３
    1.20
     thirties
    1.19
     ۳
    1.18
    2
    1.17
     dritten
    1.13
     треть
    1.09
     ३
    1.06
    Activations Density 0.040%

    No Known Activations