© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60679
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming contexts

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

    The neuron fires on morphological suffix tokens that mark English word endings—e.g. “-ation” or “-ed.”

    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
     indi
    -0.88
    一定的
    -0.85
    riendo
    -0.82
    rarr
    -0.82
    初の
    -0.81
    هاز
    -0.81
     капю
    -0.81
     autocollant
    -0.81
     гаран
    -0.80
     around
    -0.79
    POSITIVE LOGITS
     ucz
    0.85
     Vegetables
    0.81
     blemish
    0.79
    anoi
    0.77
    bigsqcup
    0.76
    nton
    0.75
     tabulated
    0.75
     kolei
    0.74
     Kili
    0.74
     Excell
    0.74
    Activations Density 0.000%

    No Known Activations