© 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. 35823
    Prev
    Next
    INDEX
    Explanations

    version, name, description, Tyrosine, Horacio, Q:

    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
     phénom
    -1.47
     zlep
    -1.43
    Kullan
    -1.38
    Waktu
    -1.36
     jednod
    -1.36
    Makanan
    -1.34
    othes
    -1.33
     合集
    -1.30
    США
    -1.30
     壁纸
    -1.30
    POSITIVE LOGITS
     is
    1.77
     was
    1.59
    T
    1.51
     H
    1.50
    </h2>
    1.47
     M
    1.44
     Y
    1.36
     T
    1.35
     J
    1.34
     V
    1.34
    Activations Density 0.000%

    No Known Activations