© 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. 130889
    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
     and
    -1.34
    N
    -1.16
    兩
    -1.08
    Affiliations
    -1.06
    p
    -1.05
    T
    -1.03
    t
    -1.00
     nedenle
    -0.98
    F
    -0.98
    P
    -0.98
    POSITIVE LOGITS
     évé
    1.47
     pleaſure
    1.28
     medier
    1.27
     poème
    1.26
    และ
    1.26
     pauvre
    1.25
     categorias
    1.25
     mystère
    1.24
     vegano
    1.23
     milj
    1.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.