© 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. 65865
    Prev
    Next
    INDEX
    Explanations

    code-related acronyms LICENSE

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

    The neuron is triggered by Caffe‐style prototxt field definitions—lines of the form “key: value,” especially when the value is a number (e.g. input_dim: 1, layer parameters, 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
     tweaking
    -0.77
     skrzy
    -0.69
    /\
    -0.67
     flimsy
    -0.67
     softness
    -0.66
    込み
    -0.66
     demonio
    -0.66
    Ariana
    -0.65
     התק
    -0.65
     /\
    -0.65
    POSITIVE LOGITS
     Seattle
    1.03
     Rainier
    0.98
     ProtoMessage
    0.96
     subgraph
    0.96
    ORT
    0.93
    Seattle
    0.92
     Operator
    0.88
     Hanford
    0.83
     Martina
    0.81
    EditPart
    0.80
    Activations Density 0.009%

    No Known Activations