© 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. 22-GEMMASCOPE-RES-131K
    7. 12390
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     what
    -1.24
     for
    -1.07
     how
    -1.02
    菁
    -1.02
    ✨:
    -1.01
     who
    -0.98
     个
    -0.96
    čios
    -0.93
     نمی
    -0.93
    getLastName
    -0.93
    POSITIVE LOGITS
     Ähnliche
    1.23
     möglicherweise
    1.19
     kategorii
    1.19
     sogar
    1.19
     醬
    1.18
     evtl
    1.16
     Sortiment
    1.16
    Minden
    1.16
     ploy
    1.14
    emballage
    1.13
    Activations Density 0.010%

    No Known Activations