© 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. 31216
    Prev
    Next
    INDEX
    Explanations

    court case citations with preceding asterisks

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

    The neuron is essentially inactive—it doesn’t respond to any tokens.

    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
     destinées
    -0.85
    ívar
    -0.84
     bronce
    -0.81
    Новый
    -0.81
     lengan
    -0.79
    ﺲ
    -0.78
    uarga
    -0.75
     autó
    -0.75
    četně
    -0.74
     Mandalorian
    -0.74
    POSITIVE LOGITS
     stalo
    0.83
    表的
    0.81
     popular
    0.78
     shock
    0.77
    anin
    0.76
     निम्नलिखित
    0.75
    Resta
    0.75
    éc
    0.73
    淏
    0.72
    piro
    0.71
    Activations Density 0.062%

    No Known Activations