© 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. 34-GEMMASCOPE-RES-131K
    4. 33477
    Prev
    Next
    INDEX
    Explanations

    corrosion and environments

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

    terms related to material corrosion, degradation, and failure in technical or engineering contexts.

    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
    terea
    -0.80
    obtenir
    -0.76
    ganta
    -0.75
    apunov
    -0.73
    specification
    -0.72
    utto
    -0.71
    Ton
    -0.71
    付き合い
    -0.69
    oherty
    -0.69
    inerario
    -0.69
    POSITIVE LOGITS
    emb
    1.02
     fret
    0.96
     emb
    0.94
     cracking
    0.91
     environments
    0.91
     attack
    0.90
    attack
    0.90
    environments
    0.87
     Environments
    0.87
     environment
    0.84
    Activations Density 0.035%

    No Known Activations