© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16023
    Prev
    Next
    INDEX
    Explanations

    personal feelings and qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    真剣
    -1.02
    iální
    -0.94
     incredibly
    -0.88
    なかな
    -0.85
     extremely
    -0.85
     variational
    -0.84
    ≃
    -0.84
     paradise
    -0.84
    chappen
    -0.84
     traits
    -0.83
    POSITIVE LOGITS
     symbolic
    0.94
     at
    0.94
    symbolic
    0.93
     tradicional
    0.91
     having
    0.91
     feeling
    0.90
     want
    0.89
     symbolically
    0.88
     feels
    0.88
     it
    0.87
    Activations Density 0.047%

    No Known Activations