© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2655
    Prev
    Next
    INDEX
    Explanations

    microanalysis and spectrometry

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

    scientific analysis techniques and laboratory methods.

    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
     witchcraft
    -0.77
     Bernice
    -0.74
    Jawab
    -0.74
     ממ
    -0.73
     sorcery
    -0.73
     annexation
    -0.72
    電腦
    -0.71
     Beschwerden
    -0.69
    하며
    -0.69
     allzu
    -0.69
    POSITIVE LOGITS
     micro
    1.29
    micro
    1.28
     procedure
    1.16
     микро
    1.11
     quantitative
    1.11
     macro
    1.08
     Micro
    1.08
    routine
    1.05
     determination
    1.04
    Micro
    1.04
    Activations Density 0.125%

    No Known Activations