© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68572
    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
     any
    -1.11
    Sabes
    -1.08
     });
    -1.07
     Bildschirm
    -1.07
    codings
    -1.06
     ఇ
    -1.05
     dorados
    -1.02
     });
    
    -1.02
     tandis
    -1.02
     }));
    -1.00
    POSITIVE LOGITS
     uiteindelijk
    1.18
     nă
    1.01
     and
    1.01
    According
    0.98
    écial
    0.97
     будет
    0.94
     schéma
    0.93
     lê
    0.93
    מנו
    0.92
     hippo
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.