© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113025
    Prev
    Next
    INDEX
    Explanations

    buy online products

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

    The neuron fires strongly on explicit purchase‐intent phrases (e.g. “buy X,” “authentic Y,” “order Z”) identifying calls to action to buy a product.

    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
    剮
    -1.29
    »:
    -1.25
    )».
    -1.24
    assade
    -1.22
     olika
    -1.21
    providedIn
    -1.20
    ?»
    -1.20
    Χ
    -1.20
    "]["
    -1.19
     segni
    -1.19
    POSITIVE LOGITS
    .
    1.45
     faptul
    1.42
     they
    1.27
     Perhaps
    1.27
     자신
    1.25
     from
    1.24
     môže
    1.24
     it
    1.24
     kopling
    1.21
     Asked
    1.20
    Activations Density 0.041%

    No Known Activations