© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14705
    Prev
    Next
    INDEX
    Explanations

    established lore persona brand

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

    The neuron fires on verbs (often past‐participle or gerund forms) that describe the state of software or files in technical‐support or installation instructions—e.g. “installed,” “downloading,” “exist,” “appear,” “available.”

    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
     बल्ले
    0.78
     sadde
    0.75
    %)
    0.73
     exons
    0.73
    ень
    0.72
     litoral
    0.72
     Feedback
    0.72
     detailing
    0.71
    =((
    0.71
     Divers
    0.70
    POSITIVE LOGITS
    نیا
    0.86
    िश्वत
    0.79
     regolare
    0.78
    يروس
    0.77
     कठिना
    0.75
    owego
    0.74
    ओएस
    0.74
    ﺝ
    0.74
     रूम
    0.73
    يتها
    0.73
    Activations Density 0.001%

    No Known Activations