© 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. 78527
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and functions

    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
     Azevedo
    -0.83
     during
    -0.75
     gaining
    -0.74
     orien
    -0.74
     Creating
    -0.74
     create
    -0.72
     Providing
    -0.70
     creating
    -0.70
     providing
    -0.69
     concentrate
    -0.69
    POSITIVE LOGITS
    VARS
    0.94
    SetUp
    0.89
     SetUp
    0.85
    씁
    0.83
    houettes
    0.83
     varsity
    0.82
     그녀
    0.81
     Varsity
    0.81
     destaque
    0.81
     vendu
    0.81
    Activations Density 0.007%

    No Known Activations