© 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. 36207
    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
     minne
    -1.13
     bronz
    -1.09
     broderie
    -1.09
     palme
    -1.06
     Himmels
    -1.05
     burch
    -1.05
     keramik
    -1.04
     jari
    -1.04
     sirup
    -1.03
    YNAMICS
    -1.02
    POSITIVE LOGITS
    ఱ
    1.01
     langen
    1.00
     arbetar
    1.00
     voľ
    0.97
    ۲۱
    0.97
     seule
    0.95
    不应该
    0.93
     ...,
    0.93
     Ebenezer
    0.92
    含义
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.