© 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. 127344
    Prev
    Next
    INDEX
    Explanations

    go:generate, +build directives

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

    This neuron fires on PHP “@ORM\…” annotation lines (e.g. Doctrine ORM annotations like @ORM\Entity()).

    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
    ↵↵↵
    -1.48
     []:
    -1.46
     When
    -1.44
     из
    -1.38
     three
    -1.37
     aikaa
    -1.35
    $
    -1.34
     \
    -1.32
    用来
    -1.31
     after
    -1.29
    POSITIVE LOGITS
    EVERY
    1.39
     aint
    1.38
    龊
    1.36
     appartamento
    1.34
    تے
    1.32
     also
    1.30
     erfordert
    1.29
    忤
    1.29
     lijkt
    1.28
    Análisis
    1.28
    Activations Density 0.023%

    No Known Activations