© 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. 117448
    Prev
    Next
    INDEX
    Explanations

    "another win", Q:

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

    The neuron activates on third‐person plural past‐tense constructions (e.g. “they were…”).

    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
    Coach
    -0.80
     adverten
    -0.79
     Earth
    -0.77
     sveta
    -0.74
     future
    -0.74
    一辈子
    -0.73
    égorie
    -0.73
    registry
    -0.73
     coach
    -0.72
     Coach
    -0.71
    POSITIVE LOGITS
     сегодняшний
    0.85
     Tahoe
    0.81
     executable
    0.77
    颊
    0.73
    ╛
    0.72
    cionada
    0.72
    glVertex
    0.72
    ्य
    0.71
    aree
    0.71
    enada
    0.70
    Activations Density 0.009%

    No Known Activations