© 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. 95746
    Prev
    Next
    INDEX
    Explanations

    Christian contexts

    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_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
     
    -2.89
    の関係
    -2.34
    でて
    -2.31
    を始め
    -2.28
     ofrecen
    -2.28
     prendre
    -2.27
     intric
    -2.25
    の魅力
    -2.20
     soooo
    -2.19
    
    -2.19
    POSITIVE LOGITS
    }
    2.64
     mardi
    2.30
    ");
    2.22
    ))$_
    2.22
    from
    2.22
    酲
    2.19
     thema
    2.16
    ization
    2.14
     bedste
    2.14
     roj
    2.13
    Activations Density 0.007%

    No Known Activations