© 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. 34-GEMMASCOPE-RES-131K
    7. 495
    Prev
    Next
    INDEX
    Explanations

    air and water movement

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

    weather and atmospheric phenomena, particularly descriptions of wind, currents, and air movements.

    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
    rı
    -0.79
    koľ
    -0.74
    ijão
    -0.73
    antara
    -0.72
    НИЯ
    -0.71
    Sla
    -0.69
    剣
    -0.69
     absolue
    -0.68
     enfans
    -0.68
    wanych
    -0.68
    POSITIVE LOGITS
     currents
    3.27
     Currents
    2.34
     drafts
    2.30
    currents
    2.30
     corrientes
    2.27
     draft
    2.25
    draft
    1.90
     convection
    1.89
     draughts
    1.87
     courants
    1.80
    Activations Density 0.043%

    No Known Activations