© 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. 22-GEMMASCOPE-RES-131K
    7. 73495
    Prev
    Next
    INDEX
    Explanations

    code syntax and variable declarations

    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_22/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
     new
    -1.38
     requirements
    -1.25
     request
    -1.10
     research
    -1.10
     necessary
    -1.09
     testing
    -1.09
     requirement
    -1.05
     name
    -1.04
     kirch
    -1.03
     robot
    -1.00
    POSITIVE LOGITS
     gourmand
    1.14
     också
    1.08
     Atención
    1.05
     donker
    1.00
    훙
    0.96
     kanilang
    0.95
    밈
    0.94
    ؓ
    0.94
    :'#
    0.93
     största
    0.93
    Activations Density 0.003%

    No Known Activations