© 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. 28570
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    つまり
    -1.27
     other
    -1.20
    福田
    -1.16
     alkoh
    -1.16
    郵便局
    -1.09
     kakak
    -1.09
    海鮮
    -1.07
     maler
    -1.07
    などを
    -1.07
     therefore
    -1.07
    POSITIVE LOGITS
     and
    2.23
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.33
     odası
    1.30
    ↵↵↵↵↵↵↵↵↵↵
    1.30
     sonidos
    1.29
     kılıf
    1.29
    Reak
    1.28
    ruimte
    1.26
     vergeten
    1.26
    Activations Density 0.115%

    No Known Activations