© 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. 11493
    Prev
    Next
    INDEX
    Explanations

    problems presents

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

    The neuron fires on words that signal problems, difficulties, or glitches (e.g. “problems,” “trouble,” “issues,” “glitches”).

    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
    決して
    0.57
     ब्रेन
    0.57
     guérison
    0.55
     Ly
    0.52
    Brain
    0.50
     Brain
    0.50
     Simulation
    0.49
    俗
    0.49
    毬
    0.48
    ersi
    0.48
    POSITIVE LOGITS
     problems
    3.11
     trouble
    2.94
    problems
    2.89
     problemas
    2.88
     problemen
    2.84
     Problems
    2.83
     troubles
    2.81
    Problems
    2.81
     probleme
    2.77
     problèmes
    2.73
    Activations Density 0.614%

    No Known Activations