© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71548
    Prev
    Next
    INDEX
    Explanations

    prefix phrases

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

    The neuron is essentially inactive—it never lights up and thus doesn’t detect any pattern.

    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
     tigre
    -1.07
    larak
    -1.04
     torres
    -1.02
     leopardo
    -1.02
    ondissement
    -1.02
    widual
    -0.98
     complemento
    -0.98
    tku
    -0.97
    nimi
    -0.96
     tomates
    -0.96
    POSITIVE LOGITS
    M
    1.09
     daños
    0.98
    T
    0.98
    B
    0.96
    S
    0.95
     conoscenza
    0.94
    s
    0.93
    g
    0.90
    F
    0.90
     his
    0.89
    Activations Density 0.000%

    No Known Activations