© 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. 13218
    Prev
    Next
    INDEX
    Explanations

    linear algebra, regression, equations, programming

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

    The neuron consistently activates on the three‐letter sequence “Lin” (as a token prefix in words like Linpack, Lincoln, Linoleic, Linworth, etc.).

    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
    ปาก
    0.55
    }]{
    0.53
     glace
    0.52
    certificates
    0.52
    ั้น
    0.52
    subtract
    0.52
    mettre
    0.52
     Gipps
    0.52
     سنت
    0.51
     aquell
    0.50
    POSITIVE LOGITS
     Lin
    0.70
     lin
    0.70
    Lin
    0.69
     林
    0.65
     arm
    0.64
    林
    0.63
     リン
    0.63
    動
    0.60
     LIN
    0.59
    啁
    0.58
    Activations Density 0.060%

    No Known Activations