© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2596
    Prev
    Next
    INDEX
    Explanations

    questions about what I

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

    The neuron responds strongly to commercial transaction terms—especially words about booking or renting services and their costs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    7
    0.57
    8
    0.50
    明確
    0.49
    둑
    0.47
    5
    0.45
    充分
    0.44
    清晰
    0.43
    广泛
    0.42
     vivid
    0.42
    充足
    0.41
    POSITIVE LOGITS
     terceros
    0.63
     هذه
    0.59
     questa
    0.57
     quero
    0.56
     proyecto
    0.56
     necesitas
    0.56
     mutta
    0.55
     llevan
    0.55
     quiero
    0.55
     lleva
    0.55
    Activations Density 0.010%

    No Known Activations