© 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. 79809
    Prev
    Next
    INDEX
    Explanations

    real life

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

    The neuron strongly activates on mentions of the hairstyle “dreadlocks.”

    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
    ata
    -1.05
    ini
    -1.00
    ‐
    -1.00
    łej
    -1.00
    ı
    -0.99
    IMPORTED
    -0.98
    ubuntu
    -0.98
    錐
    -0.94
     Farmers
    -0.94
    messungen
    -0.93
    POSITIVE LOGITS
     реаль
    1.80
     real
    1.35
     реально
    1.27
     IRL
    1.25
     actual
    1.23
     podob
    1.18
    実際に
    1.17
     fakta
    1.17
     مشابه
    1.15
     irl
    1.12
    Activations Density 0.042%

    No Known Activations