© 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. 87286
    Prev
    Next
    INDEX
    Explanations

    product descriptions

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

    The neuron fires on product descriptions or promotional claims—i.e. sentences naming a product and stating its features or benefits.

    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
    om
    -1.57
    j
    -1.55
    or
    -1.54
    on
    -1.52
    to
    -1.50
    m
    -1.45
    TokenNameDOT
    -1.45
    ul
    -1.44
    p
    -1.44
    along
    -1.42
    POSITIVE LOGITS
    ťaž
    1.52
    pasti
    1.45
    砚
    1.41
     instruk
    1.40
    kusi
    1.39
    contoh
    1.39
     feminist
    1.38
    indahan
    1.36
    kursi
    1.36
     just
    1.34
    Activations Density 0.152%

    No Known Activations