© 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. 58817
    Prev
    Next
    INDEX
    Explanations

    heat and brood

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

    references to heating, temperature, or thermal conditions in scientific and technical texts.

    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
     store
    -0.71
     przeci
    -0.69
     recommandé
    -0.69
    compare
    -0.68
    rasında
    -0.67
    odendron
    -0.66
     Tym
    -0.66
     cup
    -0.66
     notables
    -0.65
    AZA
    -0.65
    POSITIVE LOGITS
     broiler
    1.74
     bro
    1.45
     grill
    1.33
     Bro
    1.30
     BRO
    1.11
    Bro
    1.06
     Grill
    1.01
    bro
    1.01
    BRO
    1.00
     emitter
    0.96
    Activations Density 0.013%

    No Known Activations