© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93832
    Prev
    Next
    INDEX
    Explanations

    Q: or "Specific IgE" or "Short Summary"

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

    This neuron detects formal biographical statements about someone’s service or appointment under a historical figure (e.g. “served under,” “was given,” “put to death,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     welche
    -0.99
     must
    -0.95
    прочем
    -0.87
     "...
    -0.84
     which
    -0.80
    へと
    -0.79
    Damn
    -0.79
    TokenNameDOT
    -0.78
    埃及
    -0.78
    Which
    -0.77
    POSITIVE LOGITS
    =[];
    0.91
     barva
    0.90
     jednod
    0.89
     černá
    0.86
    %%\
    0.86
    voller
    0.85
    !!.
    0.84
     différentes
    0.84
     différents
    0.84
    Rath
    0.83
    Activations Density 0.003%

    No Known Activations