© 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. 14984
    Prev
    Next
    INDEX
    Explanations

    i.e. or that is

    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
    Recept
    -1.05
     शुर
    -1.02
    Čo
    -0.99
    Kval
    -0.98
    Dobrý
    -0.93
     mundos
    -0.91
    Kolor
    -0.91
    ledning
    -0.91
     plantas
    -0.90
    𝕪
    -0.89
    POSITIVE LOGITS
     either
    1.37
    either
    1.22
    Either
    1.11
    is
    0.97
    ie
    0.97
    i
    0.96
     cioè
    0.96
     entweder
    0.93
    “
    0.91
     Either
    0.89
    Activations Density 0.121%

    No Known Activations