© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14800
    Prev
    Next
    INDEX
    Explanations

    reviewing items or subjects

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

    The neuron detects promotional or commercial blog‐post language—things like “review,” “giveaway,” “sponsored,” “affiliate,” etc.

    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
     will
    -1.77
    MatIconModule
    -1.38
     is
    -1.38
     notion
    -1.34
     details
    -1.32
     his
    -1.31
     lists
    -1.30
     himself
    -1.30
    MatButtonModule
    -1.28
     ensured
    -1.27
    POSITIVE LOGITS
    gemaakt
    1.35
     sés
    1.34
    лтемелер
    1.34
     gouttes
    1.31
    ｀*)
    1.31
     cramped
    1.30
    ल
    1.28
    ueuse
    1.27
     ilyen
    1.27
    seits
    1.27
    Activations Density 0.034%

    No Known Activations