© 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. 34-GEMMASCOPE-RES-131K
    7. 117626
    Prev
    Next
    INDEX
    Explanations

    sadness and negative emotions

    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
     provincias
    -0.95
    铆
    -0.89
     страх
    -0.85
     wied
    -0.81
     takut
    -0.79
     terkenal
    -0.79
    statuses
    -0.78
    kyard
    -0.78
    isio
    -0.77
    ែ
    -0.77
    POSITIVE LOGITS
     sad
    2.59
     saddened
    2.41
     sadd
    2.39
     Sad
    2.13
    Sad
    2.08
     Sadd
    1.97
     SAD
    1.73
    sad
    1.73
     sadness
    1.59
     saddest
    1.56
    Activations Density 0.018%

    No Known Activations