© 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. 1318
    Prev
    Next
    INDEX
    Explanations

    The neuron responds strongly to words ending in “-ing,” i.e. present-participle or gerund verb forms.

    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
    /
    0.45
     respectiv
    0.45
     series
    0.45
    =
    0.44
     S
    0.44
     /
    0.43
    '
    0.42
    I
    0.42
     I
    0.42
     B
    0.42
    POSITIVE LOGITS
     allerlei
    0.53
     বেশকিছু
    0.50
     some
    0.47
     никаких
    0.47
     considerable
    0.46
     numerous
    0.45
     zahlreiche
    0.45
     பல்வேறு
    0.45
     these
    0.44
     everything
    0.44
    Activations Density 1.233%

    No Known Activations