© 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. 109593
    Prev
    Next
    INDEX
    Explanations

    opens new window or tab

    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
     ltd
    -0.78
    oue
    -0.78
    rances
    -0.77
     pz
    -0.76
    warz
    -0.75
     ljudi
    -0.75
    mbolos
    -0.75
     meraih
    -0.75
     Leck
    -0.74
     бать
    -0.71
    POSITIVE LOGITS
     new
    2.03
     separate
    1.37
     external
    1.24
    在新
    1.23
    new
    1.23
     új
    1.17
     Separate
    1.16
     opens
    1.16
     in
    1.14
     seperate
    1.09
    Activations Density 0.030%

    No Known Activations