© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11
    Prev
    Next
    INDEX
    Explanations

    The neuron flags capitalized proper nouns—especially brand, product, or organization names.

    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
    ATION
    0.38
    =
    0.34
     }
    0.33
     에서
    0.33
     จาก
    0.33
     进行
    0.33
    _{\
    0.33
     그리고
    0.33
     )
    0.31
    \]
    0.30
    POSITIVE LOGITS
     no
    0.75
     lots
    0.61
     plenty
    0.60
     minimal
    0.60
     emphasis
    0.59
     regard
    0.59
     fanfare
    0.59
     regards
    0.58
     a
    0.56
     caveats
    0.56
    Activations Density 0.493%

    No Known Activations