© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49495
    Prev
    Next
    INDEX
    Explanations

    fungi and mushrooms

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

    scientific names of fungi and mushroom species.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on scientific genus or species names of fungi (e.g. Amanita, Ganoderma, Agaricus, Basidiomycetes, 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
    pronounced
    -0.80
     abstracto
    -0.73
    ériques
    -0.71
    corrência
    -0.71
    eiro
    -0.70
     exor
    -0.69
    wani
    -0.69
     przys
    -0.67
    Apis
    -0.67
     Minuten
    -0.65
    POSITIVE LOGITS
     gills
    0.81
     Aman
    0.81
     imperf
    0.80
     toad
    0.78
    存储
    0.76
     bracket
    0.75
     helpful
    0.74
    пят
    0.73
     mushrooms
    0.72
    redning
    0.71
    Activations Density 0.039%

    No Known Activations