© 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. 58504
    Prev
    Next
    INDEX
    Explanations

    legal or technical document structures

    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
     installed
    -0.81
     سق
    -0.77
    腦
    -0.76
    totally
    -0.73
    ComponentScan
    -0.73
    setH
    -0.71
    riter
    -0.70
     Falling
    -0.69
    Falling
    -0.69
     Installed
    -0.68
    POSITIVE LOGITS
    CLS
    0.80
    COC
    0.73
    Smith
    0.68
     Smith
    0.68
     sạch
    0.68
     undeveloped
    0.67
    лерея
    0.65
     guitars
    0.65
    SMITH
    0.64
     Irishman
    0.64
    Activations Density 0.059%

    No Known Activations