© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106930
    Prev
    Next
    INDEX
    Explanations

    layout and alignment

    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
    aliere
    -0.76
    Joo
    -0.73
     Joo
    -0.71
     santa
    -0.69
    ipelago
    -0.69
    xFFFFFF
    -0.67
     reliever
    -0.66
    振り返
    -0.66
    祖母
    -0.66
    四川
    -0.66
    POSITIVE LOGITS
     alignment
    1.48
     Alignment
    1.38
    Alignment
    1.36
     layout
    1.33
    align
    1.28
     layouts
    1.25
    layout
    1.21
     align
    1.20
    alignment
    1.20
    setLayout
    1.16
    Activations Density 0.066%

    No Known Activations