© 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. 22-GEMMASCOPE-RES-131K
    4. 68977
    Prev
    Next
    INDEX
    Explanations

    syndrome, acid, receptor, column, ferritin

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

    technical terms and specific nomenclature across scientific, mathematical, and programming domains.

    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_22/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
     DELLE
    -0.92
     стаття
    -0.92
     malah
    -0.88
    šno
    -0.85
     justru
    -0.83
     kenal
    -0.82
    ئيس
    -0.81
    。「
    -0.78
     incríveis
    -0.78
    زو
    -0.77
    POSITIVE LOGITS
     revêtement
    0.92
    dhism
    0.92
    窪
    0.91
    焱
    0.88
     Pn
    0.86
    EDY
    0.85
    aturen
    0.85
    AGEM
    0.85
    dermal
    0.84
    lně
    0.84
    Activations Density 0.067%

    No Known Activations