© 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. 10-GEMMASCOPE-RES-131K
    7. 105751
    Prev
    Next
    INDEX
    Explanations

    official status or duties

    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
     också
    -1.83
     também
    -1.64
     étrang
    -1.49
     also
    -1.42
    炒め
    -1.41
     también
    -1.33
     أيضا
    -1.30
     επίσης
    -1.28
     kokos
    -1.28
     quelquefois
    -1.27
    POSITIVE LOGITS
     by
    1.38
     team
    1.29
     its
    1.28
     current
    1.23
     previous
    1.16
     pul
    1.15
     running
    1.14
     use
    1.13
     until
    1.13
     discussion
    1.13
    Activations Density 0.071%

    No Known Activations