© 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. 26728
    Prev
    Next
    INDEX
    Explanations

    code comparison conditions

    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
     into
    -1.18
    setViewName
    -0.90
     vitale
    -0.86
    nachron
    -0.85
     incluso
    -0.84
     ชุด
    -0.83
    verages
    -0.82
     インナー
    -0.81
     максима
    -0.80
     производство
    -0.79
    POSITIVE LOGITS
     or
    1.37
    没错
    1.18
     then
    1.09
     damaligen
    1.01
    或者是
    0.97
     hạ
    0.95
     this
    0.95
     both
    0.94
     when
    0.90
     atunci
    0.89
    Activations Density 0.008%

    No Known Activations