© 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. 22-GEMMASCOPE-RES-131K
    7. 68530
    Prev
    Next
    INDEX
    Explanations

    code type suffixes and separators

    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
     for
    -1.04
     with
    -1.00
     before
    -0.97
     wildly
    -0.97
     that
    -0.97
     Δια
    -0.96
     so
    -0.93
     comfort
    -0.92
     new
    -0.91
     took
    -0.91
    POSITIVE LOGITS
    }:{
    1.20
     and
    1.10
     pueden
    1.08
     וכן
    1.08
    ὲν
    1.06
     medlemmer
    1.03
    ContentAlignment
    1.03
    Kval
    1.01
     resultaten
    1.01
    Če
    1.00
    Activations Density 0.015%

    No Known Activations