© 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. 58750
    Prev
    Next
    INDEX
    Explanations

    serum/plasma concentrations

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

    mentions of blood or plasma measurements in medical/scientific 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
    alarme
    -0.99
     qualsiasi
    -0.97
    grains
    -0.94
     $("
    -0.88
     garantir
    -0.86
     Centurion
    -0.85
     tramit
    -0.82
    fiant
    -0.82
     vuol
    -0.82
     другая
    -0.81
    POSITIVE LOGITS
     concentrations
    1.10
     and
    1.03
     concentration
    1.00
     levels
    0.98
     level
    0.89
     contains
    0.87
    ✂
    0.82
     Levels
    0.76
     Wellen
    0.75
     conc
    0.74
    Activations Density 0.163%

    No Known Activations