© 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. 22-GEMMASCOPE-RES-131K
    7. 129167
    Prev
    Next
    INDEX
    Explanations

    The neuron spikes on multi‐syllable, domain‐specific technical or scientific terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    location followed by equals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ímica
    -0.96
    вање
    -0.94
    ǒ
    -0.87
     adhesives
    -0.85
    انا
    -0.84
    Andres
    -0.83
    镠
    -0.82
     rov
    -0.81
     Escolar
    -0.81
     \'
    -0.81
    POSITIVE LOGITS
     trouvera
    1.07
     geg
    0.99
     Hül
    0.92
    じゃあ
    0.92
     snow
    0.91
     apprécier
    0.90
     verona
    0.90
     вернуться
    0.90
     profumo
    0.89
     toutes
    0.88
    Activations Density 0.155%

    No Known Activations