© 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. 53849
    Prev
    Next
    INDEX
    Explanations

    code and math variables

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

    This neuron detects occurrences of function definitions (including lambdas) by picking up on the parameter names (e.g. “x,” “y,” “series”) in code.

    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
     and
    -1.09
     as
    -1.05
    ”,
    -0.95
    </
    -0.92
     with
    -0.90
    )。
    -0.89
    "],
    -0.88
    ),
    -0.88
    ”?
    -0.85
    "/>
    -0.83
    POSITIVE LOGITS
    presumably
    1.10
    locally
    0.95
    violation
    0.94
    Ensure
    0.93
    despite
    0.93
    🛵
    0.91
     teken
    0.90
     perspek
    0.90
     soixante
    0.90
     粉色
    0.88
    Activations Density 0.020%

    No Known Activations