© 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. 91784
    Prev
    Next
    INDEX
    Explanations

    coconut palms

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

    mentions of coconut and tropical items in text.

    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
     От
    -0.82
    ACTER
    -0.75
     Blumen
    -0.74
     изменя
    -0.73
     Frog
    -0.73
    ולים
    -0.72
    혀
    -0.70
    Horace
    -0.66
     blueberry
    -0.66
     Kapoor
    -0.66
    POSITIVE LOGITS
     palm
    2.33
     palms
    2.16
    Palm
    2.02
     Palm
    1.95
     Palms
    1.92
    palm
    1.91
     паль
    1.71
     coconut
    1.52
     palma
    1.41
    🌴
    1.35
    Activations Density 0.016%

    No Known Activations