© 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. 10-GEMMASCOPE-RES-131K
    7. 66832
    Prev
    Next
    INDEX
    Explanations

    abscess

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

    medical terms related to abscesses in clinical and medical contexts.

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

    The neuron activates on occurrences of “abscess” and its morphological variants.

    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
    </strong>
    -2.73
    ם
    -2.58
    ztés
    -2.25
    骉
    -2.20
    辿
    -2.19
    ৢ
    -2.08
    
    -2.08
    麼
    -2.08
     {
    -2.05
    矇
    -2.05
    POSITIVE LOGITS
    𞤢
    2.56
    ཫ
    2.48
    </td>
    2.45
    _
    2.36
    ;
    2.22
    槩
    2.20
    俁
    2.17
    和她
    2.16
    鹮
    2.13
    T
    2.09
    Activations Density 0.005%

    No Known Activations