© 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. 109123
    Prev
    Next
    INDEX
    Explanations

    explaining reasons or beliefs

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

    The neuron spots sentences that open with or heavily feature first‐person pronouns (I, we) indicating a personal statement or opinion.

    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
     even
    -2.20
     навіть
    -1.84
     даже
    -1.78
     however
    -1.70
     incluso
    -1.69
     should
    -1.66
     nawet
    -1.59
     sogar
    -1.53
     bahkan
    -1.53
    Should
    -1.42
    POSITIVE LOGITS
    实在是
    1.48
    找不到
    1.31
     justement
    1.27
    實在
    1.23
     such
    1.21
     przecież
    1.12
     zoveel
    1.11
    实在
    1.09
     so
    1.06
     believes
    1.06
    Activations Density 0.061%

    No Known Activations