© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 301
    Prev
    Next
    INDEX
    Explanations

    expressing strong likes

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

    the main thing this neuron does is find mentions of personal leisure activities or hobbies.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    breviations
    -1.34
     this
    -1.17
    聋
    -1.06
     that
    -1.02
     separados
    -1.00
    涣
    -0.97
     aanzien
    -0.96
     потрі
    -0.94
     not
    -0.93
    rous
    -0.93
    POSITIVE LOGITS
     erity
    1.15
     especially
    1.10
     frequentemente
    1.05
    bilen
    1.05
     family
    1.05
     surtout
    1.04
     soprattutto
    1.02
    餚
    1.01
     Teilnahme
    1.01
    studium
    1.00
    Activations Density 0.004%

    No Known Activations