© 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. 77571
    Prev
    Next
    INDEX
    Explanations

    in environments and tissues

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

    phrases describing substances or elements within environmental contexts.

    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
    关键字
    -0.87
    vény
    -0.84
     selenium
    -0.84
    fragment
    -0.83
     اطلاعات
    -0.81
    IZONT
    -0.79
     буй
    -0.79
     atrás
    -0.79
     acides
    -0.75
    imshow
    -0.73
    POSITIVE LOGITS
     bloodstream
    1.39
     soils
    1.32
     soil
    1.28
     tissues
    1.16
     atmosphere
    1.14
     foods
    1.13
     our
    1.08
     diets
    1.06
     saliva
    1.03
     system
    1.02
    Activations Density 0.218%

    No Known Activations