© 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. 34-GEMMASCOPE-RES-131K
    4. 56135
    Prev
    Next
    INDEX
    Explanations

    start of specific phrases and words

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

    The neuron never activates on any of these inputs (all activation values are zero), so it appears to be inactive and isn’t detecting any pattern.

    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
    гӀ
    -0.94
     Descripción
    -0.90
    بانی
    -0.87
     سیاه
    -0.83
     اندروید
    -0.80
     genomen
    -0.74
     Clause
    -0.72
    Rae
    -0.71
    aminan
    -0.71
    Descripción
    -0.71
    POSITIVE LOGITS
    this
    0.88
    Этот
    0.85
     this
    0.84
     @"/
    0.82
    过了
    0.81
    ectin
    0.80
    この
    0.79
     этот
    0.79
     этой
    0.78
    ваги
    0.75
    Activations Density 0.000%

    No Known Activations