© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15397
    Prev
    Next
    INDEX
    Explanations

    javascript and python code

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

    the names of programming languages, frameworks, and other software-development technologies.

    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
    COMPUTER
    0.76
    電腦
    0.73
    檎
    0.72
     any
    0.71
    ન
    0.71
     électronique
    0.70
    APPLE
    0.67
    {$\
    0.67
    ELECTRON
    0.66
    电脑
    0.66
    POSITIVE LOGITS
     stipend
    0.88
    र्ती
    0.84
     kennis
    0.83
     liet
    0.83
     nugget
    0.82
     kader
    0.82
    ěla
    0.82
    ěstí
    0.81
     berätt
    0.80
    చ్చి
    0.80
    Activations Density 0.001%

    No Known Activations