© 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. 8812
    Prev
    Next
    INDEX
    Explanations

    means or implies

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

    The neuron fires on formal second-person address (you/your/Users) in policy or terms‐of‐service style statements.

    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
     crept
    0.65
     още
    0.59
     लागू
    0.59
     ससु
    0.59
    얇
    0.59
    垂
    0.57
     sprouted
    0.57
    🄰
    0.57
     ferret
    0.57
    角落
    0.57
    POSITIVE LOGITS
    必定
    0.79
     must
    0.77
     guarantees
    0.77
     implies
    0.74
     involves
    0.73
     подразуме
    0.73
     means
    0.72
    必然
    0.71
     you
    0.70
     bedeutet
    0.70
    Activations Density 0.593%

    No Known Activations