© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35179
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

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

    The neuron fires on closing‐block markers (e.g. a `}` in code or the `</…>` of an HTML tag).

    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
     one
    -1.85
     all
    -1.59
     like
    -1.45
     from
    -1.21
     also
    -1.20
     for
    -1.16
     In
    -1.14
     not
    -1.10
     as
    -1.10
     most
    -1.09
    POSITIVE LOGITS
     mogą
    1.25
    老者
    1.12
    whenever
    1.10
    convenient
    1.10
    soon
    1.09
     diriger
    1.09
     заболевания
    1.09
     corriger
    1.07
     faciliter
    1.06
     cierra
    1.06
    Activations Density 0.012%

    No Known Activations