© 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. 68986
    Prev
    Next
    INDEX
    Explanations

    words starting with ab

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

    The neuron activates on the letter sequence “ab,” in particular when it appears as the start of a word (e.g. “abate,” “abberate,” “abridge,” etc.).

    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
    」，
    -2.86
    </h3>
    -2.48
    ことはありません
    -2.44
    quelize
    -2.23
    ことはない
    -2.22
    袛
    -2.19
    鹮
    -2.17
    獁
    -2.17
    事は
    -2.14
    ほうが
    -2.13
    POSITIVE LOGITS
    *
    3.36
     or
    2.27
     $\
    2.22
    1
    2.20
    馀
    2.13
     Tatsache
    2.09
    3
    2.06
     joy
    2.03
    \
    2.02
    7
    2.02
    Activations Density 0.006%

    No Known Activations