© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115454
    Prev
    Next
    INDEX
    Explanations

    undefined control sequence

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

    This neuron is triggered by the vertical‐bar symbol (“|”), as used in code (e.g. Ruby block parameter delimiters).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    InBytes
    -0.69
     несколько
    -0.69
    ocene
    -0.65
    Ă
    -0.65
    sores
    -0.65
     encontrarás
    -0.65
    .............
    -0.64
     RANGE
    -0.64
     سين
    -0.64
     личности
    -0.64
    POSITIVE LOGITS
    NECTION
    0.69
    eket
    0.68
    シェ
    0.68
     Hazel
    0.65
    irements
    0.64
    itigen
    0.63
    setPassword
    0.62
    ♜
    0.61
     նաև
    0.61
     Without
    0.60
    Activations Density 0.073%

    No Known Activations