© 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. 10-GEMMASCOPE-RES-131K
    7. 87185
    Prev
    Next
    INDEX
    Explanations

    medical remission

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

    medical terms related to disease remission in clinical contexts.

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

    The neuron activates on the word "remission," identifying mentions of a medical condition returning to a disease‐free or inactive state.

    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
    the
    -3.44
    a
    -2.94
    0
    -2.69
    ’
    -2.63
    o
    -2.34
     "
    -2.30
    }
    -2.25
    ᠂
    -2.22
    ]
    -2.22
    J
    -2.17
    POSITIVE LOGITS
    乆
    2.88
    <td>
    2.47
    呿
    2.39
    PARATION
    2.31
    哢
    2.22
     Aviso
    2.19
    ⏑
    2.16
     TÉCNICA
    2.13
    TryDecode
    2.11
    ﮟ
    2.09
    Activations Density 0.011%

    No Known Activations