© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59967
    Prev
    Next
    INDEX
    Explanations

    firewood burning stove

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    PhysRev
    -0.91
     reefs
    -0.85
    いぐるみ
    -0.82
    findUser
    -0.81
    Jugador
    -0.80
    🎸
    -0.80
    electro
    -0.79
     Resta
    -0.77
     neón
    -0.77
     град
    -0.75
    POSITIVE LOGITS
     stove
    1.12
     wood
    1.06
     pellet
    0.97
    薪
    0.97
     burn
    0.91
    Wood
    0.91
     EPA
    0.87
     flue
    0.86
     номина
    0.84
     Overnight
    0.82
    Activations Density 0.011%

    No Known Activations