© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108410
    Prev
    Next
    INDEX
    Explanations

    text alignment and padding

    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
    weebly
    -0.88
     innovative
    -0.82
     melalui
    -0.81
    rophore
    -0.78
    南部
    -0.75
    smartphone
    -0.73
     photography
    -0.73
     Photographie
    -0.73
    During
    -0.72
     different
    -0.72
    POSITIVE LOGITS
     %-
    1.80
    %-
    1.59
     setw
    1.41
    Pad
    1.10
    Spaces
    1.05
    spaces
    1.02
    setw
    1.01
    pads
    0.97
     vér
    0.96
     cột
    0.96
    Activations Density 0.008%

    No Known Activations