© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11221
    Prev
    Next
    INDEX
    Explanations

    add with completion

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

    This neuron detects technical code and API/library references (e.g. framework or class names, callback‐based or reactive constructs).

    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
    Landau
    0.62
     inviscid
    0.59
     العلا
    0.55
    碁
    0.55
    惬
    0.52
    チン
    0.52
    ปรา
    0.51
    マウス
    0.51
     गिनी
    0.50
    靶
    0.50
    POSITIVE LOGITS
    retrofit
    0.87
     AsyncTask
    0.84
     BuildConfig
    0.81
    getStringExtra
    0.80
     retrofit
    0.77
     android
    0.77
    mData
    0.75
     MainActivity
    0.74
    requestCode
    0.73
    hilt
    0.73
    Activations Density 0.006%

    No Known Activations