© 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. 91366
    Prev
    Next
    INDEX
    Explanations

    code, license, or legal text

    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
     INDEX
    -0.85
     INTERFACE
    -0.80
    ixi
    -0.76
    gegevens
    -0.71
     ساخته
    -0.71
    IDAS
    -0.67
    MAG
    -0.67
    INDEX
    -0.67
     columnIndex
    -0.65
    醣
    -0.65
    POSITIVE LOGITS
    ḇ
    0.67
    ここから
    0.66
    ontes
    0.66
     outwards
    0.65
    lifies
    0.64
     sources
    0.64
     Wel
    0.63
     alga
    0.63
    丐
    0.62
     spleen
    0.62
    Activations Density 0.055%

    No Known Activations