© 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. 4425
    Prev
    Next
    INDEX
    Explanations

    aspirations

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

    The neuron activates on formal legal and policy terminology, such as references to law, courts, legal bases, and data‐protection terms.

    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
     Temperature
    0.82
    A
    0.79
    ，
    0.79
    1
    0.79
    E
    0.78
    O
    0.77
     Time
    0.77
     Tonic
    0.77
     ，
    0.76
    so
    0.75
    POSITIVE LOGITS
     purportedly
    1.30
     defamatory
    1.23
     allegedly
    1.20
     purported
    1.16
     якобы
    1.14
     allegations
    1.12
     undisclosed
    1.07
     alleging
    1.04
     alleges
    1.04
     alleged
    1.01
    Activations Density 0.289%

    No Known Activations