© 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. 75474
    Prev
    Next
    INDEX
    Explanations

    issue or regression

    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
    ➡️
    -1.47
    💁
    -1.30
    💫
    -1.29
    😲
    -1.25
    💃
    -1.25
     to
    -1.24
    💸
    -1.23
    😨
    -1.20
    它
    -1.20
    💐
    -1.19
    POSITIVE LOGITS
     you
    1.93
     będziesz
    1.48
     cuyo
    1.41
     niektórych
    1.38
    อื่น
    1.37
     erwähnten
    1.37
    ソフトウェア
    1.33
     during
    1.31
     besseren
    1.30
     możesz
    1.30
    Activations Density 0.128%

    No Known Activations