© 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. 710
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for adjectives or descriptors that express positive evaluation or high performance/quality.

    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
    0.51
     January
    0.51
     September
    0.48
     ২৮
    0.45
     მხოლოდ
    0.41
     bruk
    0.41
    ̂
    0.40
     USSR
    0.40
     ৩৮
    0.40
     ผม
    0.40
    POSITIVE LOGITS
    Notifications
    0.47
    ።
    0.46
    。</
    0.46
    clearfix
    0.45
    .。
    0.45
    まとめて
    0.44
    Ｈ
    0.43
    といった
    0.43
    他们的
    0.42
     bequem
    0.42
    Activations Density 0.000%

    No Known Activations