© 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. 123907
    Prev
    Next
    INDEX
    Explanations

    mysql database usage

    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
     But
    -2.86
     was
    -2.86
     we
    -2.72
    を始め
    -2.64
     is
    -2.63
     they
    -2.41
    但我
    -2.39
     However
    -2.38
     isn
    -2.36
     Again
    -2.31
    POSITIVE LOGITS
    The
    2.56
    .
    2.42
    _
    2.41
    its
    2.33
    F
    2.28
     veränder
    2.20
    s
    2.17
    းက
    2.08
     them
    2.05
    抬手
    2.05
    Activations Density 0.008%

    No Known Activations