© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36480
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     gwaran
    -1.50
     every
    -1.49
     its
    -1.47
     both
    -1.36
     all
    -1.32
     each
    -1.30
    dekat
    -1.27
    𝐃
    -1.27
     camisetas
    -1.26
     Bretaña
    -1.26
    POSITIVE LOGITS
    u
    1.45
    is
    1.39
    g
    1.30
    U
    1.18
    ist
    1.18
    k
    1.16
    ru
    1.16
    N
    1.15
     stalwart
    1.13
    ith
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.