© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13131
    Prev
    Next
    INDEX
    Explanations

    hardware and system settings

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

    The neuron fires on technical software‐install and maintenance language—especially version numbers, update steps, and related jargon.

    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_31_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
    螓
    0.61
    ność
    0.56
    炎
    0.55
    ไม
    0.55
     охо
    0.54
    ismarck
    0.54
    め
    0.54
     kêu
    0.53
    滨
    0.53
     messagebox
    0.52
    POSITIVE LOGITS
     android
    0.91
     Android
    0.83
    Android
    0.77
    android
    0.76
    droid
    0.76
     андроид
    0.69
    ANDROID
    0.68
     OnePlus
    0.68
     nitrogen
    0.67
    constraintlayout
    0.66
    Activations Density 0.058%

    No Known Activations