© 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. 43640
    Prev
    Next
    INDEX
    Explanations

    Mie, MCM, SMD, retin, rolex, tinnitus, SBS

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

    The neuron fires on multi‐letter wordpieces that serve as the stems of technical or specialized terms—especially acronyms (e.g. MCM, SMD) and common roots (e.g. retin- in retinopathy, Mie- in Mie goreng).

    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
    “
    -3.05
    \
    -2.75
    er
    -2.61
    *
    -2.61
    ”.
    -2.58
    to
    -2.55
    ल
    -2.38
    ’
    -2.31
    ل
    -2.31
     彼女
    -2.30
    POSITIVE LOGITS
    汌
    3.39
    Ꮸ
    2.70
    ൎ
    2.61
    쨩
    2.55
    enablog
    2.47
    接下来的
    2.47
    replyreport
    2.36
    odils
    2.34
    푘
    2.34
    开车
    2.33
    Activations Density 0.025%

    No Known Activations