© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67170
    Prev
    Next
    INDEX
    Explanations

    Di prefix

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

    The neuron specifically detects the subword token “Di,” i.e. words beginning with the letters D-i.

    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
    richlet
    -2.44
    蓥
    -2.36
    鲠
    -2.28
     dificuldades
    -2.25
     they
    -2.25
    to
    -2.23
     a
    -2.23
    ви
    -2.20
     welchen
    -2.20
    ↵
    -2.19
    POSITIVE LOGITS
    俛
    2.89
    鼉
    2.75
    猡
    2.63
    呿
    2.61
    *
    2.42
    名叫
    2.36
    蚍
    2.36
    缡
    2.31
    壜
    2.31
     sabah
    2.31
    Activations Density 0.019%

    No Known Activations