© 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. 116897
    Prev
    Next
    INDEX
    Explanations

    moisture and mold damage

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

    words related to moisture, dampness, water damage, and mold.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Burner
    -0.92
    ⛽
    -0.85
     zand
    -0.82
    WireFormat
    -0.80
     incin
    -0.79
    ственное
    -0.79
     sharpening
    -0.77
     хиру
    -0.77
     sharpness
    -0.76
     burners
    -0.76
    POSITIVE LOGITS
     moisture
    2.45
     mold
    1.89
     Moisture
    1.86
     damp
    1.80
    moisture
    1.71
    Moisture
    1.70
     water
    1.66
     humidity
    1.64
     mould
    1.57
     wet
    1.47
    Activations Density 0.025%

    No Known Activations