© 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. 131030
    Prev
    Next
    INDEX
    Explanations

    words and numbers with specific meanings

    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
     information
    -1.40
     data
    -1.27
     osv
    -1.23
     changes
    -1.23
     Also
    -1.20
     with
    -1.12
     as
    -1.12
     शुर
    -1.11
    Also
    -1.10
     characteristics
    -1.10
    POSITIVE LOGITS
     TWENTY
    1.20
     Dinas
    1.09
     stalwart
    1.06
     dezen
    1.05
     FIF
    1.05
     cependant
    1.05
     HUND
    1.05
     momente
    1.03
     إعادة
    1.03
    偶尔
    1.01
    Activations Density 0.000%

    No Known Activations