© 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. 78856
    Prev
    Next
    INDEX
    Explanations

    plant names and place names

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

    The neuron selectively activates on plant-related terms (especially the names of fruits, flowers, and other botanical items).

    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
     abſ
    -0.89
    久しぶりに
    -0.88
     durian
    -0.85
    gus
    -0.82
     juſt
    -0.82
    diator
    -0.81
    рные
    -0.81
     autenti
    -0.80
     seam
    -0.80
     facelift
    -0.79
    POSITIVE LOGITS
     leaves
    1.28
     leaf
    1.11
    leaves
    1.08
    leaf
    1.06
     Leaves
    1.05
     Grove
    1.03
     Leaf
    0.93
     Hill
    0.90
     seed
    0.88
     seeds
    0.88
    Activations Density 0.042%

    No Known Activations