© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 60762
    Prev
    Next
    INDEX
    Explanations

    code structures and data assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ussure
    -1.49
    }$\\
    -1.41
    actéristi
    -1.38
     }));
    -1.37
     itemprop
    -1.36
     }),
    -1.34
     endif
    -1.32
     )
    
    -1.30
    ,:)
    -1.30
     reine
    -1.29
    POSITIVE LOGITS
     alrededores
    1.62
     these
    1.41
     kuhusu
    1.40
     ambao
    1.39
    だったので
    1.34
     about
    1.34
    了啊
    1.30
     baratas
    1.27
     übri
    1.27
     that
    1.27
    Activations Density 0.040%

    No Known Activations