© 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. 73039
    Prev
    Next
    INDEX
    Explanations

    expressions of error

    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
     a
    -1.58
    e
    -1.50
     juf
    -1.41
    called
    -1.34
    が悪
    -1.27
    onthe
    -1.27
     actuellement
    -1.23
    Y
    -1.22
    )
    -1.22
     distrik
    -1.22
    POSITIVE LOGITS
     sizeable
    1.45
    綵
    1.41
     their
    1.37
    　※
    1.33
     sizable
    1.32
     came
    1.31
    魔兽
    1.30
    êque
    1.29
    ،
    1.29
    However
    1.28
    Activations Density 0.012%

    No Known Activations