© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38069
    Prev
    Next
    INDEX
    Explanations

    biological and scientific contexts

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

    terms related to biology and ecology, particularly prefixes like "bio-" in words such as bioaccumulation, biofilm, and biomonitor.

    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
    distributions
    -0.88
    ffichage
    -0.77
     הצ
    -0.75
     biologist
    -0.74
    Subscribe
    -0.73
    ährung
    -0.72
    iments
    -0.71
    descriptions
    -0.71
    谊
    -0.69
    utilities
    -0.68
    POSITIVE LOGITS
    objc
    0.74
     indie
    0.74
    гим
    0.73
     nickel
    0.70
     Georgie
    0.69
     MSG
    0.69
     demais
    0.69
    brooke
    0.69
     tort
    0.68
     hoe
    0.68
    Activations Density 0.036%

    No Known Activations