© 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. 39394
    Prev
    Next
    INDEX
    Explanations

    product model suffixes

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

    The neuron is specialized in detecting numeric tokens (e.g. model years, specifications, and product model 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_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
    ようです
    -1.60
    ことも
    -1.55
    ようになります
    -1.52
    えっ
    -1.42
    ことが
    -1.41
    あー
    -1.38
    際には
    -1.38
    為に
    -1.36
    it
    -1.35
    さぁ
    -1.34
    POSITIVE LOGITS
    <bos>
    1.57
    がありますが
    1.45
    を持っている
    1.44
    があるので
    1.37
    pherals
    1.36
    معرفی
    1.30
    もあります
    1.29
    UCIÓN
    1.29
    があります
    1.26
    けどね
    1.26
    Activations Density 0.032%

    No Known Activations