© 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. 91839
    Prev
    Next
    INDEX
    Explanations

    summer activities and times

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

    The neuron fires on title‐style headings (capitalized or section‐header words) that mark the start of a labeled section.

    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
     Christmas
    -1.80
     Halloween
    -1.77
     christmas
    -1.70
    christmas
    -1.57
     summer
    -1.53
     winter
    -1.49
     autumn
    -1.41
     Xmas
    -1.38
    Christmas
    -1.32
     Thanksgiving
    -1.30
    POSITIVE LOGITS
     tradition
    0.91
    ἥ
    0.90
    今年は
    0.90
    korn
    0.84
    Nosotros
    0.82
     пирог
    0.80
     profi
    0.79
     traditions
    0.78
    minLength
    0.78
    去年
    0.77
    Activations Density 0.050%

    No Known Activations