© 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. 34868
    Prev
    Next
    INDEX
    Explanations

    lists, headings, or questions

    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
     frivolous
    -0.82
     población
    -0.78
    릭터
    -0.77
    電腦
    -0.76
     Compatibility
    -0.75
     válvula
    -0.75
     Pemain
    -0.74
    getProducts
    -0.74
     мысль
    -0.74
    logio
    -0.73
    POSITIVE LOGITS
     白
    0.98
    看看
    0.88
     жид
    0.86
    pa
    0.85
     vase
    0.83
    annique
    0.82
    uti
    0.81
    isc
    0.81
    TokenNameR
    0.80
    ini
    0.78
    Activations Density 0.000%

    No Known Activations