© 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. 518
    Prev
    Next
    INDEX
    Explanations

    just to confirm/say/be

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

    This neuron detects the discourse‐marker/filler word “just” used for emphasis or to begin remarks.

    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
    es
    0.37
     czyli
    0.35
     மற்றும்
    0.35
     (!
    0.34
     ie
    0.33
     upravo
    0.33
    },
    0.33
    または
    0.32
     Also
    0.32
    0.32
    POSITIVE LOGITS
    ifiably
    0.72
    ifiable
    0.42
     muốn
    0.42
     kidding
    0.38
    แค่
    0.38
     ഒന്ന്
    0.38
    ifying
    0.37
     хотела
    0.37
    ificação
    0.37
     FYI
    0.37
    Activations Density 0.304%

    No Known Activations