© 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. 101706
    Prev
    Next
    INDEX
    Explanations

    TypeError programming errors

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

    the word "TypeError" in programming code and error messages.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on occurrences of the term “TypeError,” i.e. when a TypeError exception is mentioned.

    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
    🌻
    -1.88
    🫡
    -1.88
    😹
    -1.79
    🧡
    -1.77
    }$
    -1.73
    👏👏
    -1.71
     created
    -1.70
    埸
    -1.70
     improve
    -1.69
     想
    -1.69
    POSITIVE LOGITS
    Ἢ
    2.16
     about
    2.11
    ญี่ป
    1.94
     нескольких
    1.80
    親切
    1.79
    勦
    1.77
    ݮ
    1.77
    ༀ
    1.76
     наша
    1.71
     raras
    1.70
    Activations Density 0.001%

    No Known Activations