© 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. 38420
    Prev
    Next
    INDEX
    Explanations

    one of the

    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
     and
    -2.02
    這個
    -1.85
    pography
    -1.45
    0
    -1.45
    這種
    -1.44
     ganger
    -1.44
    this
    -1.43
    这种
    -1.41
    iamo
    -1.39
    はその
    -1.35
    POSITIVE LOGITS
     membres
    1.48
     wielu
    1.44
    след
    1.43
     gering
    1.43
    ULDER
    1.42
     所以
    1.39
     hijos
    1.38
     moet
    1.37
     kuchni
    1.37
     dispozici
    1.36
    Activations Density 0.034%

    No Known Activations