© 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. 28219
    Prev
    Next
    INDEX
    Explanations

    potential and achievability

    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
    antaranya
    -1.08
    naires
    -0.99
    viene
    -0.94
     känns
    -0.93
    psum
    -0.93
    telah
    -0.91
     sjø
    -0.91
     sortes
    -0.90
     vilket
    -0.90
    harapkan
    -0.90
    POSITIVE LOGITS
     if
    1.78
     achievable
    1.75
     если
    1.56
     attainable
    1.37
    只要
    1.37
     can
    1.35
     jika
    1.30
    สามารถ
    1.28
     можно
    1.23
     solutions
    1.20
    Activations Density 0.056%

    No Known Activations