© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112379
    Prev
    Next
    INDEX
    Explanations

    geographical locations and biomes

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

    terms related to specific ecological biomes, particularly taiga, tundra, savanna, and boreal forests.

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

    The neuron specializes in detecting mentions of ecological biome names (e.g., major habitat types).

    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
    珰
    -2.92
    塍
    -2.89
    饪
    -2.80
    𖥦
    -2.66
    蛱
    -2.48
    煐
    -2.47
    ॣ
    -2.44
    舠
    -2.31
    $',
    -2.28
    葙
    -2.27
    POSITIVE LOGITS
     he
    3.42
     '
    2.33
     of
    2.16
     approximate
    2.09
     outrage
    2.08
    of
    2.06
     специаль
    1.95
     обслуживание
    1.95
    恣
    1.93
     altre
    1.92
    Activations Density 0.002%

    No Known Activations