© 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. 100922
    Prev
    Next
    INDEX
    Explanations

    lichen planus or food patties

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

    The neuron fires on low‐frequency, domain‐specific tokens—i.e. uncommon or technical words.

    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
     kleinere
    -3.39
     längere
    -2.94
     ストレッチ
    -2.92
    珰
    -2.89
     bessere
    -2.63
    罍
    -2.55
    阏
    -2.55
     eenig
    -2.55
     verbess
    -2.53
     eene
    -2.52
    POSITIVE LOGITS
     When
    3.67
    replyreport
    3.16
    \
    2.97
    —
    2.89
    </td>
    2.58
    (
    2.58
    ">
    2.56
    ???
    2.53
     recieved
    2.45
    g
    2.44
    Activations Density 0.011%

    No Known Activations