© 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. 22-GEMMASCOPE-RES-131K
    4. 54086
    Prev
    Next
    INDEX
    Explanations

    concepts and findings

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

    The neuron fires on abstract, nominalized nouns—especially those formed with suffixes like “-tion,” “-ance,” or “-ence” (e.g., resistance, determination, defined).

    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
     acestea
    -1.34
     this
    -1.27
    なども
    -1.20
    内容は
    -1.19
    d
    -1.15
     these
    -1.14
    それも
    -1.14
    al
    -1.13
    f
    -1.10
    3
    -1.08
    POSITIVE LOGITS
     to
    1.68
    "")
    1.42
    toit
    1.27
     miniaturka
    1.27
     tunik
    1.27
     Pozna
    1.24
     pistolet
    1.24
    ☹
    1.23
     konflikt
    1.22
    katalog
    1.20
    Activations Density 0.048%

    No Known Activations