© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14720
    Prev
    Next
    INDEX
    Explanations

    JSON object structures

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

    The neuron fires on JSON structural punctuation (braces, brackets, quotes, colons, commas, 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_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
     from
    -1.89
     and
    -1.67
     as
    -1.63
     of
    -1.60
     by
    -1.45
     but
    -1.30
     for
    -1.26
     if
    -1.24
     or
    -1.24
     should
    -1.23
    POSITIVE LOGITS
     douze
    1.25
     consistente
    1.22
     contenta
    1.20
    還在
    1.20
     totul
    1.20
    看來
    1.18
    取决
    1.18
     新作
    1.18
    後面
    1.16
     culoare
    1.14
    Activations Density 0.143%

    No Known Activations