© 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. 62905
    Prev
    Next
    INDEX
    Explanations

    stigma and normalization of mental health

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

    content related to mental health, wellness, and social issues.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    纪
    -0.93
     autón
    -0.82
     særlig
    -0.81
    ]^{
    -0.81
    setResult
    -0.81
    ᵛ
    -0.80
    fim
    -0.79
     рез
    -0.79
     Koz
    -0.78
    戯
    -0.77
    POSITIVE LOGITS
     normalize
    2.22
     stigma
    2.13
    Stig
    1.93
     normalization
    1.86
     stig
    1.81
     Stig
    1.77
     taboo
    1.72
    stig
    1.71
     stigmati
    1.69
    normalize
    1.61
    Activations Density 0.041%

    No Known Activations