© 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. 8507
    Prev
    Next
    INDEX
    Explanations

    food and health choices

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

    The neuron fires on technical how-to wiring instructions—especially phrases about wiring a switch (e.g. “how to wire a [single-pole] switch”).

    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
    0.38
     you
    0.37
     do
    0.35
     your
    0.35
     no
    0.34
     s
    0.34
     p
    0.33
     d
    0.32
     a
    0.32
     l
    0.32
    POSITIVE LOGITS
    تالي
    0.33
    olojik
    0.29
    듑
    0.29
    awcy
    0.28
    osť
    0.28
    kében
    0.28
     whanne
    0.28
     messageFields
    0.28
    서
    0.28
     thisStudent
    0.27
    Activations Density 0.003%

    No Known Activations