© 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. 54536
    Prev
    Next
    INDEX
    Explanations

    code delimiters

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

    The neuron fires on string‐delimiter quotes (the double‐quote characters that begin or end string literals).

    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
    alucía
    -1.45
     zeven
    -1.42
     confirme
    -1.42
     vijf
    -1.36
    licitations
    -1.34
     denkt
    -1.32
    NVIDIA
    -1.32
     gekocht
    -1.30
     türk
    -1.29
     sillas
    -1.29
    POSITIVE LOGITS
     only
    1.54
     will
    1.42
     includes
    1.30
     bisschen
    1.26
     from
    1.26
     result
    1.25
     used
    1.20
     currently
    1.20
     allow
    1.20
     usually
    1.20
    Activations Density 0.011%

    No Known Activations