© 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. 83745
    Prev
    Next
    INDEX
    Explanations

    blood and related conditions

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

    words related to blood or hematology, particularly terms beginning with "haem" or "hemo".

    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
    àng
    -0.82
    蔽
    -0.77
     dovuto
    -0.75
     outlawed
    -0.73
    akteur
    -0.73
    iciais
    -0.73
    高校生
    -0.72
     boyunca
    -0.71
    izophren
    -0.71
    Johannes
    -0.70
    POSITIVE LOGITS
     haem
    1.04
     Hem
    0.95
     Haem
    0.89
    toma
    0.80
     malign
    0.79
     HEM
    0.77
    leb
    0.76
    Haem
    0.76
     RAID
    0.76
     Haskell
    0.75
    Activations Density 0.053%

    No Known Activations