© 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. 24-GEMMASCOPE-2-RES-16K
    7. 419
    Prev
    Next
    INDEX
    Explanations

    This neuron lights up on the main topical or informational keywords (the salient content nouns and verbs) in a passage.

    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_24_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
     =
    0.47
     it
    0.45
     này
    0.42
    =
    0.39
    '
    0.39
     (=
    0.39
    ()
    0.38
     there
    0.38
     }
    0.37
    }
    0.37
    POSITIVE LOGITS
     다양한
    0.52
     विभिन्न
    0.51
     allerlei
    0.51
     பல்வேறு
    0.50
    様々な
    0.50
     विविध
    0.49
    বিভিন্ন
    0.48
     számos
    0.48
     çeşitli
    0.48
     zahlreichen
    0.48
    Activations Density 12.520%

    No Known Activations