© 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. 10-GEMMASCOPE-RES-131K
    7. 20833
    Prev
    Next
    INDEX
    Explanations

    coniferous trees and pines

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

    scientific names of tree species, particularly pine and fir varieties.

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

    The neuron activates on substrings naming conifer trees and related terms (e.g. “pine,” “Pinus,” “Abies,” “taiga,” 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_10/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
    ]}{
    -1.58
    🌼
    -1.52
    rentina
    -1.49
    🦋
    -1.42
    🤩
    -1.41
    헛
    -1.41
    🥰
    -1.40
    creek
    -1.38
     }}{\
    -1.38
    rageous
    -1.37
    POSITIVE LOGITS
    </h3>
    1.74
     '
    1.50
    4
    1.45
    new
    1.38
     others
    1.33
     ‘
    1.32
     hervorge
    1.31
    such
    1.30
     today
    1.30
    </i>
    1.30
    Activations Density 0.019%

    No Known Activations