© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106576
    Prev
    Next
    INDEX
    Explanations

    religious or legal figures

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

    The neuron fires on apostrophe characters (i.e. the single-quote token in possessives or quoted text).

    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
     booty
    -0.79
    DetailView
    -0.77
    nivel
    -0.77
     backpack
    -0.77
     Dirty
    -0.74
    ASSESSMENT
    -0.74
    ည်
    -0.74
    Oscill
    -0.73
     buồn
    -0.73
    ợi
    -0.72
    POSITIVE LOGITS
     każde
    0.75
    Present
    0.72
     voeding
    0.71
     pfle
    0.71
    之色
    0.69
     новое
    0.69
     откро
    0.69
    курен
    0.69
     râ
    0.68
     Ciências
    0.68
    Activations Density 0.006%

    No Known Activations