© 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. 13639
    Prev
    Next
    INDEX
    Explanations

    pair of, nested primers, encoder which, stack cloud, way forwards

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

    The neuron fires on compound technical jargon or multi‐part domain‐specific terms (e.g. “private key,” “full-stack,” “nested PCR,” “autoencoder,” “transceivers”).

    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
     várias
    -0.88
     يول
    -0.86
     beberapa
    -0.86
     women
    -0.85
     tygod
    -0.84
     cooperación
    -0.83
     femenina
    -0.82
    topics
    -0.82
     χρόν
    -0.82
     trabalhar
    -0.82
    POSITIVE LOGITS
     extremes
    0.94
     fontsize
    0.92
    UpDown
    0.91
    イヤレス
    0.88
    ♻
    0.88
     кольцо
    0.87
     terv
    0.87
    transQ
    0.85
    autoFocus
    0.84
    adaan
    0.83
    Activations Density 0.116%

    No Known Activations