© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49795
    Prev
    Next
    INDEX
    Explanations

    events happening

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

    The neuron is looking for question‐ or problem-statement trigger words and function-word sequences (e.g. “what is…,” “why is this…,” “the problem is…,” “from,” “this,” “is”).

    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
    jected
    -0.83
    RIZ
    -0.75
     %}
    -0.74
    osc
    -0.74
     थी
    -0.73
     ฮ
    -0.73
     brillantes
    -0.73
    Aziz
    -0.73
    käse
    -0.73
    juh
    -0.73
    POSITIVE LOGITS
     happen
    7.53
     happened
    7.47
     happens
    7.13
     happening
    7.00
     Happens
    4.91
    happens
    4.88
     occurs
    4.81
    happened
    4.75
    happen
    4.72
     occurred
    4.66
    Activations Density 0.392%

    No Known Activations