© 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. 34-GEMMASCOPE-RES-131K
    7. 80742
    Prev
    Next
    INDEX
    Explanations

    bears most of the blame

    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_34/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
     extrinsic
    -0.80
    åd
    -0.72
    ﾟ)
    -0.69
    ällor
    -0.68
     overcame
    -0.65
     común
    -0.65
    bgColor
    -0.65
    श्यक
    -0.65
     ejerc
    -0.65
    によ
    -0.65
    POSITIVE LOGITS
     bear
    5.03
     bears
    4.81
     bearing
    4.41
    bear
    4.03
    Bear
    3.78
    bearing
    3.78
    bears
    3.64
     Bear
    3.61
     Bears
    3.34
     shoulder
    3.31
    Activations Density 0.070%

    No Known Activations