© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71352
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    The neuron fires on passive‐voice scientific verbs reporting findings or occurrences (e.g. “found,” “discovered,” “shown,” “occur”).

    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
     and
    -2.08
     about
    -1.79
     queste
    -1.77
    %">
    -1.63
    </b>
    -1.52
     questi
    -1.52
     a
    -1.50
     something
    -1.43
    ↵↵↵
    -1.38
     essas
    -1.36
    POSITIVE LOGITS
     撮っ
    1.61
     their
    1.50
     comparaison
    1.46
     Combien
    1.41
    Hermoso
    1.35
    hmä
    1.34
     Psic
    1.32
    Koordin
    1.31
    ฅ
    1.30
     υπάρχ
    1.30
    Activations Density 0.575%

    No Known Activations