© 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. 64972
    Prev
    Next
    INDEX
    Explanations

    enterococcus faecium

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

    proper nouns associated with locations, particularly Italian or ancient Roman place names.

    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
     Reichstag
    -0.72
    irsten
    -0.72
     dừng
    -0.71
    tafogo
    -0.70
     Projeto
    -0.68
     projeto
    -0.68
    捆
    -0.68
     implantation
    -0.67
    tms
    -0.66
    Salve
    -0.66
    POSITIVE LOGITS
     Etrus
    1.09
     Etr
    0.79
    fair
    0.79
    ստ
    0.77
     Tar
    0.77
    Virginia
    0.76
     Perugia
    0.75
     Determin
    0.75
    KeepAlive
    0.75
    Tar
    0.74
    Activations Density 0.022%

    No Known Activations