© 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. 93613
    Prev
    Next
    INDEX
    Explanations

    pellet combustion and biomass fuel

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

    terms related to industrial processes for processing materials, particularly torrefaction, grinding, pelletizing, and biomass conversion.

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

    This neuron responds to specialized technical or scientific jargon terms (especially long compound words like “torrefaction,” “physicochemical,” “particulate,” and “bioenergy”).

    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
     vax
    -0.82
     بھی
    -0.80
     FLAC
    -0.79
    xler
    -0.78
     desal
    -0.78
     workbench
    -0.75
    分离
    -0.75
    Comment
    -0.75
     Sentiment
    -0.74
    Bangalore
    -0.72
    POSITIVE LOGITS
     pellets
    1.31
     pellet
    1.25
     biomass
    1.08
     Pelle
    1.04
     Pel
    1.04
     pelle
    0.96
     fuel
    0.96
    pelle
    0.93
    fuel
    0.92
     Ligne
    0.89
    Activations Density 0.019%

    No Known Activations