© 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. 10-GEMMASCOPE-RES-131K
    4. 9271
    Prev
    Next
    INDEX
    Explanations

    following punctuation

    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
     and
    -1.83
    ようになる
    -1.34
    まず
    -1.33
    volles
    -1.31
    ınar
    -1.31
    }
    -1.30
    });
    -1.27
    źć
    -1.26
    bü
    -1.23
    看看
    -1.23
    POSITIVE LOGITS
     this
    1.75
     that
    1.52
     augmente
    1.48
     would
    1.45
     they
    1.41
     deixa
    1.34
     then
    1.33
     for
    1.31
     llevará
    1.30
    このまま
    1.29
    Activations Density 0.199%

    No Known Activations