© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 960
    Prev
    Next
    INDEX
    Explanations

    Rich Chocolate, pipe wire

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

    the neuron detects distinctive proper nouns and product model identifiers (e.g. brand names, model numbers, titles).

    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_31_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
    _
    0.59
     여러
    0.54
    <0xD5>
    0.53
     varias
    0.52
    category
    0.52
     masing
    0.52
     stepwise
    0.51
    .__
    0.51
    LineWidth
    0.50
     ogn
    0.50
    POSITIVE LOGITS
     Freak
    0.66
    ™,
    0.64
    ™
    0.63
     Comics
    0.60
     Productions
    0.59
     Ranch
    0.59
    ™.
    0.59
    ®,
    0.58
     Zombie
    0.58
     Podcast
    0.57
    Activations Density 1.108%

    No Known Activations