© 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. 749
    Prev
    Next
    INDEX
    Explanations

    The neuron flags key content words—especially domain-specific nouns and adjectives that carry core factual or descriptive details.

    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
    Others
    0.58
    getInstance
    0.58
    *)
    0.55
    */
    0.54
     മറ്റ
    0.54
    encji
    0.54
     了
    0.53
    ::
    0.53
    DataItem
    0.52
    irs
    0.51
    POSITIVE LOGITS
     plenty
    1.38
     lots
    1.22
     μια
    1.21
     no
    1.17
     eine
    1.16
     një
    1.16
     an
    1.12
     penchant
    1.12
     hefty
    1.09
     ample
    1.07
    Activations Density 0.910%

    No Known Activations