© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65031
    Prev
    Next
    INDEX
    Explanations

    leading cause of

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

    phrases identifying something as a "leading cause of" or "major contributor to" a negative outcome or condition.

    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_10/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
     acoged
    -1.79
     respetu
    -1.53
     einfacher
    -1.52
    RUCT
    -1.48
     maravill
    -1.48
    yla
    -1.48
    取る
    -1.48
     carreteras
    -1.45
    xase
    -1.45
    uttgart
    -1.44
    POSITIVE LOGITS
     of
    2.11
     Arhi
    1.67
     in
    1.67
     vieta
    1.66
     antena
    1.66
     farmacia
    1.66
    melons
    1.59
     brava
    1.58
     priva
    1.58
     perche
    1.56
    Activations Density 0.107%

    No Known Activations