© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58906
    Prev
    Next
    INDEX
    Explanations

    list 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_10/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
     andere
    -1.46
     annen
    -1.28
    љено
    -1.27
     dica
    -1.26
     sirop
    -1.24
     semelh
    -1.23
     monta
    -1.23
     intrig
    -1.21
    certain
    -1.21
     tatu
    -1.21
    POSITIVE LOGITS
     usually
    1.60
     still
    1.55
     while
    1.39
     for
    1.32
     akzeptieren
    1.30
     generally
    1.27
     ideally
    1.26
     mostly
    1.23
     principally
    1.21
    ↵↵
    1.19
    Activations Density 0.158%

    No Known Activations