© 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. 9506
    Prev
    Next
    INDEX
    Explanations

    bedtime story or routine

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

    This neuron mainly responds to mentions of beds and mattresses.

    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
     بوت
    0.57
     ভাতা
    0.57
     Hat
    0.56
    HDL
    0.56
    딜
    0.56
    Flash
    0.54
     worshi
    0.53
     köl
    0.53
     hat
    0.52
    Agents
    0.51
    POSITIVE LOGITS
     bed
    2.38
     beds
    2.31
     Bed
    1.93
    beds
    1.91
    床
    1.88
     bedding
    1.88
    ベッド
    1.87
     Beds
    1.87
    Bed
    1.84
     बिस्तर
    1.84
    Activations Density 0.374%

    No Known Activations