© 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. 90413
    Prev
    Next
    INDEX
    Explanations

    markup and references

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

    The neuron activates on markdown-style blockquote markers (the leading ‘>’ characters).

    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
    مار
    -0.96
    Inoltre
    -0.95
    Quindi
    -0.89
     from
    -0.89
     seemingly
    -0.87
     Those
    -0.86
     particularly
    -0.86
    Ogni
    -0.85
     at
    -0.85
    >'+
    -0.85
    POSITIVE LOGITS
    sprüng
    1.07
     العملية
    0.94
    vičius
    0.93
    OP
    0.90
     ${({
    0.90
     😁
    0.89
     wharf
    0.88
     😊
    0.88
     terminer
    0.88
    Indicates
    0.86
    Activations Density 0.001%

    No Known Activations