© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68365
    Prev
    Next
    INDEX
    Explanations

    academic/programming/names

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

    The neuron activates on occurrences of the identifier “defaultdict” (i.e. uses or imports of Python’s defaultdict).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     "
    -2.52
     
    -2.25
     Either
    -1.81
    I
    -1.77
     Honestly
    -1.77
    ."
    -1.75
     дают
    -1.66
     Basically
    -1.66
     Whatever
    -1.65
    </h2>
    -1.64
    POSITIVE LOGITS
     dezelve
    2.11
     cirka
    2.05
     всѣ
    2.02
    ⏑
    2.02
     zoude
    2.00
     vrou
    1.88
     不锈钢
    1.86
     beina
    1.86
     vann
    1.84
    romeda
    1.80
    Activations Density 0.000%

    No Known Activations