© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164628
    Prev
    Next
    INDEX
    Explanations

    resigned to avoid

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

    This neuron activates on terms related to resignations, particularly when details like names, dates, or reasons for the resignation are mentioned.

    oai_token-act-pair · gemini-2.5-flashTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    动手
    0.40
     mg
    0.37
    osen
    0.37
    お
    0.37
    tede
    0.36
    ixed
    0.36
    nable
    0.36
    便利な
    0.35
    あります
    0.34
    補
    0.34
    POSITIVE LOGITS
    sunset
    0.39
    Filling
    0.38
     KeyEvent
    0.38
     Stoke
    0.38
     रेजि
    0.37
     resistant
    0.37
     effluent
    0.37
     invoice
    0.36
     smelt
    0.36
     inoculated
    0.35
    Activations Density 0.001%

    No Known Activations