© 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. 8886
    Prev
    Next
    INDEX
    Explanations

    phrase specifying what something is

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

    The neuron flags unusually “salient” or rare content words—i.e. terms that stand out by frequency or specificity rather than common function words.

    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
    whel
    0.81
    evoluzione
    0.80
     najwy
    0.78
     espectadores
    0.78
     ljubav
    0.78
    au
    0.77
     świata
    0.77
    煂
    0.76
     vibhav
    0.76
     собственные
    0.75
    POSITIVE LOGITS
     prefer
    0.73
     retard
    0.72
     نمائ
    0.68
     sering
    0.68
     😄
    0.66
     而且
    0.65
     claiming
    0.64
     claimed
    0.64
     construed
    0.64
     معمول
    0.64
    Activations Density 0.000%

    No Known Activations