© 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. 13243
    Prev
    Next
    INDEX
    Explanations

    self and function calls

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

    The neuron strongly responds to Python function definitions and method-self references (e.g. the “def …(self, …)” pattern).

    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
    人士
    0.87
    福祉
    0.81
    枴
    0.80
    囃
    0.80
    的美
    0.79
    первых
    0.78
    嗯
    0.77
    必定
    0.75
    ﺏ
    0.75
    包
    0.75
    POSITIVE LOGITS
    ی
    0.82
     solubilities
    0.78
    )
    0.78
    croll
    0.77
    esis
    0.77
     cartridges
    0.76
    ה
    0.76
     initialized
    0.75
     compressibility
    0.75
     fathom
    0.75
    Activations Density 0.000%

    No Known Activations