© 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. 10-GEMMASCOPE-RES-131K
    7. 12537
    Prev
    Next
    INDEX
    Explanations

    feel like statements

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

    The neuron detects first-person expressions of personal feeling or inclination (e.g. “I feel/felt like…”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     verbess
    -2.22
     erweiter
    -2.14
     We
    -1.99
     types
    -1.94
     detallada
    -1.93
     methods
    -1.89
     criticisms
    -1.81
     Drittel
    -1.81
     sichere
    -1.78
     Then
    -1.76
    POSITIVE LOGITS
    埽
    2.09
     you
    2.05
    and
    2.00
    
    1.98
    >
    1.95
     και
    1.91
    </strong>
    1.91
    ਲ਼
    1.88
    neries
    1.84
     и
    1.83
    Activations Density 0.010%

    No Known Activations