© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3346
    Prev
    Next
    INDEX
    Explanations

    technical terms followed by colon

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

    The neuron detects two‐word noun compounds where a specific name is followed by a general category term (e.g. “Rain Forest Habitat,” “developer group,” “Literary Club”).

    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
    শিকান্ত
    0.64
    ড়ের
    0.63
    aping
    0.62
    𝗿
    0.59
    čkog
    0.58
    हमी
    0.57
    უკ
    0.57
     प्रूव
    0.57
     ذریع
    0.57
    ئت
    0.57
    POSITIVE LOGITS
    0.91
    0.85
    0.79
    0.75
    0.73
               
    0.71
     =
    0.70
    0.69
     gồm
    0.68
    ,
    0.68
    Activations Density 0.003%

    No Known Activations