© 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. 10-GEMMASCOPE-RES-131K
    7. 87372
    Prev
    Next
    INDEX
    Explanations

    JAVA code syntax

    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
    providedIn
    -1.71
    #}
    -1.41
    ij
    -1.36
     décembre
    -1.34
     wadah
    -1.32
    endforeach
    -1.30
     tendremos
    -1.28
    しかったです
    -1.27
     trilha
    -1.25
     Consist
    -1.24
    POSITIVE LOGITS
     olsa
    1.33
    Portály
    1.33
     savage
    1.31
     confirmó
    1.30
     поэтому
    1.30
    ↵
    1.30
    sust
    1.30
    к
    1.28
     protegida
    1.28
     mike
    1.24
    Activations Density 0.012%

    No Known Activations