© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13736
    Prev
    Next
    INDEX
    Explanations

    supplement with

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

    The neuron responds strongly to occurrences of the word “warranties” (and related phrasing) in legal-disclaimer text.

    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
    វា
    0.91
    Requirements
    0.83
     бү
    0.81
     Возможно
    0.80
    ühren
    0.79
    酲
    0.77
    㓶
    0.76
    鸰
    0.75
     equivalents
    0.75
     aspirin
    0.74
    POSITIVE LOGITS
    킴
    0.73
     λοι
    0.70
    부터
    0.64
    ece
    0.63
    г
    0.63
     impoz
    0.63
     ดิ
    0.62
     खिलाफ
    0.61
     obviamente
    0.61
    寂
    0.61
    Activations Density 0.001%

    No Known Activations