© 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. 57516
    Prev
    Next
    INDEX
    Explanations

    featherweight division

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

    The neuron activates strongly on occurrences of the substring “feather” (including its inflected or compound forms).

    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
     Bulldog
    -0.79
    Kand
    -0.79
     Greensboro
    -0.75
    înes
    -0.73
    ele
    -0.73
    rail
    -0.71
    ISSA
    -0.71
     sunflowers
    -0.71
    🚆
    -0.70
     ugl
    -0.69
    POSITIVE LOGITS
     feather
    1.39
     quill
    1.35
     Feather
    1.30
     duster
    1.30
    🪶
    1.26
    Feather
    1.23
    feather
    1.18
     boa
    1.06
     pluma
    1.06
     feathers
    1.05
    Activations Density 0.008%

    No Known Activations