© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59561
    Prev
    Next
    INDEX
    Explanations

    health-related quality of life

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

    abbreviations for "Human Resources" or technical terms like "High Resolution" (HR).

    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
    鹕
    -0.82
     pauvreté
    -0.75
     rédaction
    -0.75
     Embed
    -0.74
     コー
    -0.73
    ginx
    -0.73
     خارجی
    -0.73
    арь
    -0.71
     Entste
    -0.71
    rarity
    -0.71
    POSITIVE LOGITS
    HPV
    0.91
     Hra
    0.84
     HR
    0.84
     HRC
    0.80
     Cheryl
    0.79
    HRC
    0.79
     mengirimkan
    0.77
    João
    0.77
     marquer
    0.76
    HR
    0.76
    Activations Density 0.022%

    No Known Activations