© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66402
    Prev
    Next
    INDEX
    Explanations

    types, versions, methods, states

    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
    -0.91
    了许多
    -0.85
     составе
    -0.83
     is
    -0.78
    mitter
    -0.77
     cucharadas
    -0.77
     responsáveis
    -0.75
     demandent
    -0.74
     nutrición
    -0.74
    jure
    -0.73
    POSITIVE LOGITS
     different
    1.33
     below
    1.16
     diferentes
    1.12
    以下
    1.09
     مختلف
    1.07
    dasarkan
    1.04
    それぞれ
    1.03
    不同
    1.03
    :</
    1.02
     each
    1.02
    Activations Density 0.069%

    No Known Activations