© 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. 66193
    Prev
    Next
    INDEX
    Explanations

    linear regression and plotting

    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
    peek
    -0.77
     Kyrie
    -0.75
    NPS
    -0.75
    ȫ
    -0.74
    compared
    -0.73
     Thái
    -0.72
     сча
    -0.69
    얇
    -0.68
     stå
    -0.68
    carpus
    -0.68
    POSITIVE LOGITS
     regression
    2.58
     Regression
    2.22
     linear
    2.19
    Regression
    2.11
    regression
    2.02
     Linear
    1.80
    Linear
    1.75
     slope
    1.73
     fitted
    1.66
     line
    1.62
    Activations Density 0.037%

    No Known Activations