© 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. 34-GEMMASCOPE-RES-131K
    7. 2605
    Prev
    Next
    INDEX
    Explanations

    return value or expression

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

    The neuron strongly activates on programming‐language tokens (keywords, identifiers, and symbols) rather than natural‐language words.

    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
     spreading
    -0.89
     about
    -0.83
     developed
    -0.74
     revealed
    -0.74
     surprised
    -0.73
     here
    -0.73
     whose
    -0.73
     stopping
    -0.73
     give
    -0.72
    江苏
    -0.72
    POSITIVE LOGITS
    ESTAMP
    0.87
    matu
    0.84
    ribute
    0.82
    бин
    0.79
     pierre
    0.79
    ఊ
    0.79
    fu
    0.78
     koste
    0.77
    ¹)
    0.77
     rekla
    0.77
    Activations Density 0.001%

    No Known Activations