© 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. 14418
    Prev
    Next
    INDEX
    Explanations

    Download, Q, High, Results

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

    The neuron is triggered by backslash characters (i.e., “\” escape or markup sequences).

    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
    -1.83
     in
    -1.82
    vaného
    -1.66
    quiera
    -1.64
    
    -1.63
     cedera
    -1.62
     papir
    -1.62
     Lakukan
    -1.61
     PUSTAKA
    -1.58
     by
    -1.57
    POSITIVE LOGITS
    *
    1.64
     admiten
    1.53
    \
    1.52
    addCriterion
    1.48
     problemet
    1.45
     and
    1.44
    かっこ
    1.43
     (!__
    1.42
    <em>
    1.42
    ...
    1.36
    Activations Density 0.000%

    No Known Activations