© 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. 9146
    Prev
    Next
    INDEX
    Explanations

    specific distances or quantities

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

    The neuron fires on distinctive content words—especially uncommon or topic-specific nouns and names (e.g. “tole,” “Cost,” “time,” “x”).

    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
    steak
    0.93
    season
    0.88
    LFT
    0.86
    surgeon
    0.86
    BUF
    0.86
    speople
    0.86
     Pobl
    0.84
    s
    0.84
    PCS
    0.80
     circunfer
    0.80
    POSITIVE LOGITS
     लेकर
    0.71
    ेला
    0.69
     следует
    0.69
     dominated
    0.68
     schemes
    0.66
     perplexed
    0.64
     explic
    0.64
     berjumpa
    0.63
     inducing
    0.63
     ‚
    0.62
    Activations Density 0.000%

    No Known Activations