© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35532
    Prev
    Next
    INDEX
    Explanations

    starting with

    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
    lím
    -1.05
     also
    -1.02
    vább
    -1.01
    最後に
    -0.93
     verir
    -0.92
    Только
    -0.92
    Более
    -0.92
    gridColumn
    -0.89
    흘
    -0.87
    货币
    -0.86
    POSITIVE LOGITS
     first
    2.42
    首先
    2.14
    まず
    2.08
     starting
    2.03
     beginning
    2.00
    まずは
    2.00
     começar
    1.94
     firstly
    1.94
     empezar
    1.90
     zunächst
    1.85
    Activations Density 0.107%

    No Known Activations