© 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. 69235
    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
     uſe
    -1.38
    割と
    -1.36
    どれだけ
    -1.24
    альных
    -1.21
    eronau
    -1.20
    はっきり
    -1.20
    綺麗に
    -1.16
    きれい
    -1.16
    にします
    -1.15
    
    -1.14
    POSITIVE LOGITS
     now
    1.45
     or
    1.40
    <bos>
    1.32
     first
    1.20
    CCIÓN
    1.12
    ְּ
    1.07
    0
    1.02
    ۤ
    1.01
    薔薇
    0.96
     talleres
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.