© 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. 91173
    Prev
    Next
    INDEX
    Explanations

    understanding and sharing feelings

    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_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
    confidence
    -0.82
    MIB
    -0.77
     GRANDE
    -0.76
    OPTIM
    -0.76
     pimenta
    -0.76
     tamen
    -0.75
     positif
    -0.75
     Pursu
    -0.74
     Confidence
    -0.73
    clearInterval
    -0.73
    POSITIVE LOGITS
     empathy
    3.81
     Empathy
    3.13
     empathi
    3.09
     empathetic
    2.64
     sympathy
    2.58
     sympathize
    2.33
     sympathi
    2.20
     compassion
    2.17
     sympathetic
    1.99
     sympathies
    1.98
    Activations Density 0.028%

    No Known Activations