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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27332
    Prev
    Next
    INDEX
    Explanations

    apprehended tried plan search really reserved tabs feel misled

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

    The neuron selectively fires on content‐bearing words (nouns, verbs, adjectives, and other semantically important terms) rather than on common function 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_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
    ？？
    -1.36
    ก็
    -1.28
    <bos>
    -1.28
     mene
    -1.25
     Poder
    -1.22
    ？？？
    -1.20
    …？
    -1.20
    、、
    -1.18
     prek
    -1.17
    は
    -1.16
    POSITIVE LOGITS
     gravidez
    1.39
     sienta
    1.29
     isolado
    1.28
     evaluaciones
    1.24
     &
    1.24
     increíbles
    1.23
     imediatamente
    1.23
     sozinho
    1.21
     alugar
    1.21
     cantidades
    1.20
    Activations Density 0.086%

    No Known Activations