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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 507
    Prev
    Next
    INDEX
    Explanations

    Let variable be

    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
     啊
    -1.66
     \
    -1.57
    翆
    -1.52
     In
    -1.48
    (!__
    -1.42
    }{*}{}
    -1.38
     ???
    -1.32
     vertes
    -1.32
     даже
    -1.31
     nawet
    -1.31
    POSITIVE LOGITS
     which
    1.62
    だったので
    1.32
    ically
    1.26
    將軍
    1.22
     whose
    1.22
    えると
    1.20
     نباش
    1.20
     Überprüfung
    1.17
    czego
    1.16
     importância
    1.14
    Activations Density 0.001%

    No Known Activations