© 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. 72234
    Prev
    Next
    INDEX
    Explanations

    declaring new fake things

    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
    逡
    -0.93
    店長
    -0.91
     ayudó
    -0.90
    eurovision
    -0.90
    nextElement
    -0.88
     aslında
    -0.88
    Dario
    -0.86
     provocado
    -0.86
    }${
    -0.85
    ))=\
    -0.85
    POSITIVE LOGITS
     nieuwe
    0.97
     new
    0.95
     version
    0.94
    her
    0.89
    新
    0.88
     الجديدة
    0.86
     nowego
    0.86
     zamiast
    0.84
     replace
    0.82
    d
    0.82
    Activations Density 0.032%

    No Known Activations