© 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. 25486
    Prev
    Next
    INDEX
    Explanations

    comma-separated lists

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

    The neuron fires on runs of digits joined by hyphens (e.g. “1-5-7-8-…” style numeric codes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     собаки
    -0.88
    punten
    -0.88
    áját
    -0.86
     experimentado
    -0.85
    tifications
    -0.84
     coloque
    -0.84
     geeft
    -0.83
     bernama
    -0.82
    buj
    -0.82
     dibujado
    -0.82
    POSITIVE LOGITS
     Malvern
    0.93
     různých
    0.88
    onatos
    0.86
    ovať
    0.82
     contextLoads
    0.82
    selectAll
    0.81
    itieren
    0.81
     façon
    0.80
    mkdir
    0.80
    stuhl
    0.79
    Activations Density 0.066%

    No Known Activations