© 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. 10-GEMMASCOPE-RES-131K
    7. 39155
    Prev
    Next
    INDEX
    Explanations

    defining or naming concepts

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

    This neuron responds to long, multi-syllable words (i.e. unusually lengthy tokens).

    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
    </strong>
    -1.60
     vorige
    -1.49
    変わらない
    -1.41
    U
    -1.34
     réduire
    -1.27
     secundario
    -1.26
    lllllll
    -1.23
    篥
    -1.23
     иностранных
    -1.22
    </sup>
    -1.21
    POSITIVE LOGITS
     enri
    1.43
    してきました
    1.37
    Нам
    1.34
     our
    1.34
     oportun
    1.30
     concentra
    1.29
    bemos
    1.28
    ˒
    1.27
     adiv
    1.27
     vivas
    1.25
    Activations Density 0.125%

    No Known Activations