© 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. 107569
    Prev
    Next
    INDEX
    Explanations

    license conditions

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

    The neuron reliably fires on code‐license boilerplate markers—especially section references, parenthesized clauses, and version numbers in license headers.

    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
     during
    -0.95
     considers
    -0.91
     ostensibly
    -0.86
     time
    -0.83
     sophisticated
    -0.82
    vaných
    -0.81
     while
    -0.79
     potentially
    -0.79
    ıla
    -0.79
     after
    -0.78
    POSITIVE LOGITS
    distributions
    1.02
    ventions
    0.96
    dista
    0.95
    formatics
    0.94
     Dlatego
    0.88
    efeated
    0.88
     バッジ
    0.88
    ilding
    0.88
    demics
    0.87
    Your
    0.86
    Activations Density 0.588%

    No Known Activations