© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12951
    Prev
    Next
    INDEX
    Explanations

    warmth, comfort, and duration

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

    This neuron fires strongly on ellipsis (“…”, “...”) tokens and continuation prompts like “Continue” or “Continue reading,” i.e. markers of truncated text or “read more” links.

    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
     Bakın
    0.64
    iphat
    0.63
     ruthenium
    0.62
     Blueprint
    0.61
     Mujhe
    0.61
    㴌
    0.61
     blueprints
    0.61
     maaaring
    0.61
     catálogo
    0.61
     falsa
    0.61
    POSITIVE LOGITS
    آور
    0.65
     നന്ന
    0.59
    More
    0.57
    no
    0.57
    changes
    0.57
    range
    0.54
    ranges
    0.54
    Changes
    0.52
    ubic
    0.52
    😋
    0.52
    Activations Density 0.004%

    No Known Activations