© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21134
    Prev
    Next
    INDEX
    Explanations

    rheumatoid arthritis

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

    specialized technical or medical terms, particularly "rheumatoid arthritis", "astral", "ingress" and "egress".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is sensitive to technical or specialized content words derived from Latin or Greek roots.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     และ
    -2.44
    が上が
    -2.23
     остальные
    -2.16
    ーん
    -2.14
    のおかげ
    -2.11
     familières
    -2.09
    疍
    -2.08
     We
    -2.06
    だったり
    -2.05
     пять
    -2.03
    POSITIVE LOGITS
    s
    4.16
    ی
    2.73
    This
    2.44
     THEIR
    2.44
     If
    2.33
    当代
    2.31
    }
    2.28
    ??????
    2.28
    整合
    2.23
    !!!!!
    2.19
    Activations Density 0.004%

    No Known Activations