© 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. 34-GEMMASCOPE-RES-131K
    7. 1998
    Prev
    Next
    INDEX
    Explanations

    carbide or silicon carbide

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

    chemical compounds and materials in scientific or technical 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
    cro
    -0.74
     glass
    -0.74
    lcd
    -0.73
     oxide
    -0.71
    CNS
    -0.69
    WriteBarrier
    -0.68
    CDR
    -0.68
    cia
    -0.67
    Citation
    -0.66
     Sunday
    -0.65
    POSITIVE LOGITS
     carbide
    1.21
     Carbide
    1.02
    carb
    0.97
     carbu
    0.91
    carbu
    0.85
    ->{
    0.79
     reinforced
    0.76
     MMC
    0.76
     Inters
    0.76
     carb
    0.76
    Activations Density 0.064%

    No Known Activations