© 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. 5767
    Prev
    Next
    INDEX
    Explanations

    essay explores

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

    The neuron fires on formal academic or scholarly document cues—terms that signal sections, chapters, studies, or methodological headings.

    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
     calculator
    0.60
     calculators
    0.59
     легко
    0.57
     orthogonality
    0.55
     equivalently
    0.55
    可以直接
    0.55
     simpl
    0.54
     Calculating
    0.54
     Calculator
    0.53
     elegant
    0.52
    POSITIVE LOGITS
     ethnographic
    0.90
    enquête
    0.85
     Interviews
    0.85
     enquête
    0.84
     entrevistas
    0.80
     interviews
    0.79
    调研
    0.76
     contends
    0.75
    empirical
    0.75
     empirical
    0.74
    Activations Density 0.101%

    No Known Activations