© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65807
    Prev
    Next
    INDEX
    Explanations

    available to

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

    The neuron responds to very common, high-frequency English words (mostly function words and broadly used content words).

    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
     violenta
    -1.19
    Dermott
    -1.13
    faring
    -1.12
    一亮
    -1.11
     Offisielt
    -1.11
     saine
    -1.06
     BIBLIOGRAPHY
    -1.05
    AUS
    -1.05
     him
    -1.05
     Talvez
    -1.05
    POSITIVE LOGITS
     now
    1.72
     how
    1.52
     recibo
    1.34
    EFIAPI
    1.31
     here
    1.29
    γωγ
    1.24
     unseren
    1.23
     好看
    1.21
    zondere
    1.19
    </h3>
    1.17
    Activations Density 0.692%

    No Known Activations