© 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. 12047
    Prev
    Next
    INDEX
    Explanations

    to consider

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

    This neuron strongly activates on common small function words—especially the preposition “to.”

    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
    べく
    0.59
     pregi
    0.58
    lessly
    0.58
    ------+
    0.57
    कर्णी
    0.57
    grouped
    0.57
    capable
    0.56
    -----+
    0.55
    ත්‍
    0.54
    leşik
    0.54
    POSITIVE LOGITS
     consider
    0.99
     considerar
    0.91
     Consider
    0.90
     reckon
    0.73
    Consider
    0.71
     choose
    0.70
     beachten
    0.70
     CONSIDER
    0.69
     considérer
    0.68
     Consid
    0.68
    Activations Density 0.280%

    No Known Activations