© 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. 39371
    Prev
    Next
    INDEX
    Explanations

    HELLO field names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ḿ
    -1.10
    ӯ
    -1.09
     refroid
    -1.07
     alábbi
    -1.07
    horts
    -1.04
     bescher
    -1.02
     alcune
    -1.02
     gekocht
    -1.01
     Existen
    -0.99
     établissement
    -0.98
    POSITIVE LOGITS
     their
    1.40
     from
    1.14
     unique
    1.13
     difficult
    1.12
     so
    1.11
     unusual
    1.04
     people
    1.03
     dazzling
    1.03
     used
    1.03
    Zunanje
    1.02
    Activations Density 0.001%

    No Known Activations