© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90681
    Prev
    Next
    INDEX
    Explanations

    foam or foaming variations

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

    The neuron fires on terms referring to the formation or presence of foam (e.g. “foam,” “foaming,” “foams,” “foamed,” “froth,” “lather”).

    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
     
    -1.84
    W
    -1.84
     Einladung
    -1.68
    ?’
    -1.66
     zult
    -1.66
    需要
    -1.65
     liberi
    -1.64
    這麼
    -1.64
    ولايات
    -1.61
    もう少し
    -1.60
    POSITIVE LOGITS
     of
    1.83
    IANGLES
    1.78
    abaikan
    1.76
    沨
    1.73
     儿
    1.70
     Кур
    1.69
    accesorios
    1.65
    虓
    1.61
    院長
    1.61
     plaît
    1.60
    Activations Density 0.008%

    No Known Activations