© 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. 9621
    Prev
    Next
    INDEX
    Explanations

    writing assistance, orders establishing

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

    This neuron detects contentful action verbs (i.e. lexical verbs conveying key actions or processes).

    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
    0.71
    Ã
    0.66
    â
    0.64
    Armor
    0.64
    Orc
    0.61
    ↵↵
    0.60
    Â
    0.60
    dbo
    0.60
     그러면
    0.59
    </code>
    0.59
    POSITIVE LOGITS
    了不少
    0.98
     birçok
    0.91
     during
    0.88
     tijdens
    0.86
     by
    0.85
     podczas
    0.84
     vissa
    0.82
     számos
    0.82
     unor
    0.82
     their
    0.81
    Activations Density 0.544%

    No Known Activations