© 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. 59758
    Prev
    Next
    INDEX
    Explanations

    script including googleapis.com

    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
    🦲
    -0.77
     Abgerufen
    -0.71
     televiz
    -0.70
     względu
    -0.65
    ༝
    -0.61
    mohon
    -0.61
     prawo
    -0.61
     sanitario
    -0.60
    onomy
    -0.60
    漢字
    -0.60
    POSITIVE LOGITS
    Mass
    0.78
     Mass
    0.77
     Bas
    0.76
     Mustafa
    0.73
    게
    0.72
     Toibin
    0.71
     qualitatively
    0.71
     Jang
    0.69
     dolomite
    0.68
     şek
    0.68
    Activations Density 0.060%

    No Known Activations