© 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. 34-GEMMASCOPE-RES-131K
    7. 34534
    Prev
    Next
    INDEX
    Explanations

    TLC spots

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

    scientific terminology related to chemistry, particularly in contexts describing laboratory methods and chromatography.

    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
    mybatis
    -0.83
    tablissement
    -0.76
     nocy
    -0.73
    UNES
    -0.71
    toprule
    -0.71
    inta
    -0.71
    وص
    -0.71
     Whit
    -0.71
    tablissements
    -0.70
    Alessandro
    -0.70
    POSITIVE LOGITS
     TLC
    1.02
     spots
    1.02
     spotting
    0.99
    TLC
    0.94
    spots
    0.93
     configurar
    0.85
     Spots
    0.83
     Plates
    0.83
    Spots
    0.82
    Plates
    0.82
    Activations Density 0.021%

    No Known Activations