© 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. 34359
    Prev
    Next
    INDEX
    Explanations

    variable arguments and method calls

    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
    Deadpool
    -0.90
    Github
    -0.86
    朝着
    -0.82
     można
    -0.82
    holly
    -0.81
     escola
    -0.81
     Becca
    -0.81
    btnClose
    -0.80
    처럼
    -0.80
    findet
    -0.80
    POSITIVE LOGITS
     specific
    1.02
     may
    1.00
     usually
    0.99
     alguma
    0.83
     might
    0.83
    specific
    0.82
     Usually
    0.80
     Depending
    0.79
     additional
    0.79
    auto
    0.79
    Activations Density 0.045%

    No Known Activations