© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11976
    Prev
    Next
    INDEX
    Explanations

    microbial identification and testing

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

    scientific laboratory techniques and biological assay terms related to microorganisms.

    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_10/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
     Alquiler
    -1.42
     where
    -1.32
     rajut
    -1.30
     jopa
    -1.30
    躓
    -1.29
     faktisk
    -1.28
     actually
    -1.27
     colorida
    -1.27
    Bisous
    -1.24
    ſo
    -1.23
    POSITIVE LOGITS
     criteria
    1.33
    記者
    1.17
     criterion
    1.17
    著者
    1.09
     Acqua
    1.08
    는데
    1.05
    尊敬
    1.05
     Commute
    1.05
     Congreg
    1.03
     incorporate
    1.02
    Activations Density 0.089%

    No Known Activations