© 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. 39458
    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
    ஂ
    -1.14
     Mâ
    -1.11
     搞笑
    -1.11
    PRESSED
    -1.07
    URIDAD
    -1.01
     veröffentlich
    -1.00
     Bewußt
    -0.99
     壁纸
    -0.99
    insel
    -0.98
    蜮
    -0.96
    POSITIVE LOGITS
     ikinci
    1.17
    可能会
    1.09
    }$
    1.08
    "])){
    1.07
    可能會
    1.05
     lhe
    1.00
    ',
    0.96
    ůvod
    0.96
     \&
    0.95
     Faculty
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.