© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119739
    Prev
    Next
    INDEX
    Explanations

    health risks and conditions

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

    content about health hazards, injuries, and diseases that can cause harm to humans.

    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
     to
    -1.44
    耵
    -1.44
     selle
    -1.23
    phoenix
    -1.20
     Dicht
    -1.20
     Werken
    -1.18
     AMONG
    -1.17
     mulai
    -1.17
    吠
    -1.17
    uesday
    -1.16
    POSITIVE LOGITS
     like
    1.40
    这两个
    1.40
    Like
    1.36
    These
    1.30
    Another
    1.30
    Both
    1.27
    これらの
    1.26
     dichos
    1.25
    Such
    1.24
     albeit
    1.22
    Activations Density 0.115%

    No Known Activations