© 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. 34-GEMMASCOPE-RES-131K
    4. 118417
    Prev
    Next
    INDEX
    Explanations

    tikz plots with axes

    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
     that
    -0.82
     According
    -0.80
     Each
    -0.79
     partai
    -0.79
     during
    -0.76
    groupBy
    -0.76
     During
    -0.75
     -
    -0.75
     as
    -0.75
     disclosed
    -0.74
    POSITIVE LOGITS
     محور
    1.01
     twin
    1.00
     Nunez
    0.96
    РОВ
    0.90
    ætte
    0.90
     Harts
    0.88
    isit
    0.88
    Ax
    0.88
    ρας
    0.86
    axi
    0.85
    Activations Density 0.004%

    No Known Activations