© 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. 10-GEMMASCOPE-RES-131K
    7. 110613
    Prev
    Next
    INDEX
    Explanations

    helper in code and frameworks

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

    the word "Helper" or "helper" in programming contexts, particularly in class names and file paths.

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

    The neuron detects mentions of “Helper” (the word “helper” in class or code contexts).

    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
     damos
    -1.51
    our
    -1.46
     bonitos
    -1.43
     my
    -1.41
     surpren
    -1.40
     our
    -1.37
     createSprite
    -1.34
     eşofman
    -1.33
    憷
    -1.32
     you
    -1.30
    POSITIVE LOGITS
    1
    1.58
     considerazione
    1.48
    鱿
    1.46
    0
    1.42
    mathrm
    1.41
    降临
    1.41
    6
    1.39
     beider
    1.38
     foglie
    1.38
    8
    1.36
    Activations Density 0.001%

    No Known Activations