© 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. 77513
    Prev
    Next
    INDEX
    Explanations

    tree bark

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

    references to plant parts, particularly bark.

    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
    ിക
    -0.82
     colli
    -0.82
    ཧ
    -0.80
     plunger
    -0.80
     vergeten
    -0.79
    zeiro
    -0.75
     beachfront
    -0.75
    Nero
    -0.75
     arcane
    -0.75
     урна
    -0.74
    POSITIVE LOGITS
     bark
    2.97
    bark
    2.20
     Bark
    2.13
    Bark
    1.88
     barks
    1.62
     Barker
    1.31
     кора
    1.24
     peeling
    1.21
     cork
    1.21
     trunk
    1.21
    Activations Density 0.019%

    No Known Activations