© 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. 1868
    Prev
    Next
    INDEX
    Explanations

    mock objects and libraries

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

    The neuron strongly activates on occurrences of “mock” (in any casing or compound form, e.g. mock, Mockery, mock‐spawn, etc.).

    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
     tgt
    -0.81
     amassed
    -0.81
     لي
    -0.81
    LEVANT
    -0.80
     aeros
    -0.80
    上級
    -0.79
    ሓ
    -0.77
    ৯
    -0.77
     lautet
    -0.76
     mentioning
    -0.75
    POSITIVE LOGITS
    ument
    1.54
    ups
    1.02
     Mock
    0.94
    olate
    0.92
    tails
    0.91
    tail
    0.91
     heroic
    0.90
     mock
    0.88
    aide
    0.86
     bintang
    0.85
    Activations Density 0.008%

    No Known Activations