© 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. 98757
    Prev
    Next
    INDEX
    Explanations

    alpha subunit

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

    protein subunits and molecular components in scientific text.

    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
     setPassword
    -0.87
     inhabitants
    -0.78
     concentrated
    -0.77
     Impedance
    -0.76
     attitudes
    -0.73
     عاشق
    -0.73
     Melinda
    -0.72
     Wirt
    -0.72
     mossy
    -0.71
     Fanny
    -0.71
    POSITIVE LOGITS
     subunit
    2.97
     subunits
    2.94
     unit
    1.98
     units
    1.64
    Unit
    1.63
    unit
    1.61
     Unit
    1.52
    units
    1.46
     unidades
    1.38
    Units
    1.37
    Activations Density 0.168%

    No Known Activations