© 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. 22-GEMMASCOPE-RES-131K
    7. 75053
    Prev
    Next
    INDEX
    Explanations

    adverse events with causality

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

    descriptions of negative events or situations like injuries, arrests, lawsuits, deaths, or people in distress.

    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_22/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
    ところが
    -1.02
    錳
    -0.99
    offers
    -0.94
    を行います
    -0.93
     però
    -0.92
    now
    -0.92
     appels
    -0.92
     않았
    -0.92
     więc
    -0.91
     dunque
    -0.91
    POSITIVE LOGITS
     after
    3.45
     после
    2.48
     nachdem
    2.22
     following
    2.11
     because
    2.09
     setelah
    2.03
     після
    1.92
     após
    1.87
    after
    1.79
     when
    1.77
    Activations Density 0.183%

    No Known Activations