© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83186
    Prev
    Next
    INDEX
    Explanations

    focus and interest levels

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

    The neuron fires strongly on first‐person self‐references and accompanying emotional or reflective verbs (e.g. “I,” “myself,” “feeling,” “surprised”).

    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
     hesit
    -0.84
    lland
    -0.82
    Elli
    -0.82
     kış
    -0.82
    Redund
    -0.81
    ByID
    -0.80
     confined
    -0.79
    hicule
    -0.79
     superstitious
    -0.78
    蛍
    -0.77
    POSITIVE LOGITS
     zoned
    1.55
     tuned
    1.50
     zone
    1.49
     zoning
    1.48
     tuning
    1.47
     checked
    1.37
     tune
    1.36
    tune
    1.34
    Tune
    1.31
     glaze
    1.30
    Activations Density 0.030%

    No Known Activations