© 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. 117277
    Prev
    Next
    INDEX
    Explanations

    new initialization

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

    This neuron detects Go unit‐test function declarations (e.g. the “func TestXxx(t *testing.T)” pattern).

    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
    ureusement
    -0.88
    のではない
    -0.81
    lorin
    -0.80
    っているので
    -0.78
     aggiun
    -0.77
     моей
    -0.76
     drzwi
    -0.76
     vouloir
    -0.76
    のでしょうか
    -0.75
     maxWidth
    -0.75
    POSITIVE LOGITS
     New
    2.14
     new
    2.11
     &
    1.77
    New
    1.66
    new
    1.48
     \&
    1.40
    的新
    1.24
    新
    1.23
     NEW
    1.11
    新建
    1.10
    Activations Density 0.024%

    No Known Activations