© 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. 24-GEMMASCOPE-2-RES-16K
    7. 8380
    Prev
    Next
    INDEX
    Explanations

    stolen kisses

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

    This neuron responds to structural headings or list‐item markers (e.g. verse or section numbers and titles) rather than ordinary running text.

    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_24_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
    y
    0.80
    те
    0.75
    的東西
    0.75
    iveness
    0.73
    й
    0.73
    allax
    0.71
    ële
    0.70
    тия
    0.70
    emie
    0.70
    а
    0.69
    POSITIVE LOGITS
     adrift
    0.88
     unsatisfied
    0.87
     bystanders
    0.84
    asambhavam
    0.78
     Subsidi
    0.76
     Pritchard
    0.76
     naciones
    0.75
     sardines
    0.74
     sweeteners
    0.74
     Chloride
    0.73
    Activations Density 0.000%

    No Known Activations