© 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. 2842
    Prev
    Next
    INDEX
    Explanations

    ability to

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

    The neuron detects statements of required skills or qualifications—especially “ability to …” or similar competency and capability phrases.

    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
     graces
    0.57
     얘
    0.57
    에서도
    0.56
    comers
    0.54
    的這個
    0.53
     whereby
    0.53
    一起
    0.51
     dalamnya
    0.51
     Reprinted
    0.50
     Untitled
    0.50
    POSITIVE LOGITS
     يعمل
    0.61
    𝗮
    0.59
    أن
    0.55
     منظم
    0.54
    َل
    0.53
     تجمع
    0.52
    𝖓
    0.52
    ű
    0.52
     واضح
    0.52
    ának
    0.50
    Activations Density 0.003%

    No Known Activations