© 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. 69354
    Prev
    Next
    INDEX
    Explanations

    interior to surfaces or parts

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

    The neuron consistently activates on the word “interior,” i.e. references to the internal part of something.

    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
     —
    -2.53
    ta
    -2.36
    籥
    -2.28
     процесс
    -2.25
     avec
    -2.25
     Германия
    -2.14
     OF
    -2.09
    馓
    -2.09
    好人
    -2.06
    퐿
    -2.06
    POSITIVE LOGITS
     That
    2.77
    葙
    2.50
     светло
    2.48
    ization
    2.44
     your
    2.42
     größeren
    2.41
     “
    2.41
     creía
    2.39
    .
    2.34
    𖡼
    2.34
    Activations Density 0.003%

    No Known Activations