© 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. 22-GEMMASCOPE-RES-131K
    4. 36668
    Prev
    Next
    INDEX
    Explanations

    overall or though

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

    The neuron activates on first-person opinion or experience markers (e.g. “I,” “will,” “would,” “was,” “to do again”), i.e. personal statements of preference or intent.

    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
     حتی
    -1.32
     даже
    -1.28
     thậm
    -1.19
     bahkan
    -1.14
     even
    -1.13
    лых
    -1.05
     навіть
    -1.02
     même
    -1.00
     sogar
    -0.99
    どの
    -0.96
    POSITIVE LOGITS
     but
    2.25
     però
    1.45
     will
    1.43
     však
    1.34
     overall
    1.31
     Tuttavia
    1.24
     ولكن
    1.20
     BUT
    1.18
     pero
    1.16
     όμως
    1.16
    Activations Density 0.004%

    No Known Activations