© 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. 34-GEMMASCOPE-RES-131K
    7. 98391
    Prev
    Next
    INDEX
    Explanations

    grounds for emphasis

    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_34/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
     plafon
    -1.93
    𓁹
    -1.89
     autres
    -1.86
    𓆏
    -1.80
     alternatif
    -1.72
    糁
    -1.70
    ícias
    -1.67
    奁
    -1.66
     testé
    -1.66
     хоте
    -1.66
    POSITIVE LOGITS
     when
    3.47
     in
    3.34
     since
    3.27
     with
    3.16
     during
    3.00
     from
    2.91
     for
    2.63
     after
    2.52
     if
    2.50
     those
    2.42
    Activations Density 0.038%

    No Known Activations