© 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. 63539
    Prev
    Next
    INDEX
    Explanations

    plant size and growth

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

    plant parts and botanical structures in descriptive passages about plants.

    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
     petals
    -0.82
    unsubscribe
    -0.79
     corporativa
    -0.75
    deur
    -0.74
    闍
    -0.74
    icale
    -0.73
     ге
    -0.73
     rect
    -0.73
     মান
    -0.73
     スタンド
    -0.71
    POSITIVE LOGITS
     shoots
    1.08
     young
    1.04
     shoot
    1.00
    shoot
    0.97
    wood
    0.96
     buds
    0.91
     growth
    0.89
     older
    0.89
     younger
    0.89
     nodes
    0.87
    Activations Density 0.017%

    No Known Activations