© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25686
    Prev
    Next
    INDEX
    Explanations

    traditional approaches

    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_22/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
    ımda
    -1.17
     querían
    -1.06
    ὴν
    -1.02
    ginine
    -1.02
    Trimethyl
    -1.00
    內的
    -0.99
     quería
    -0.98
    顺利
    -0.97
    Pter
    -0.97
     particolare
    -0.96
    POSITIVE LOGITS
     traditional
    1.95
    traditional
    1.88
     тради
    1.63
    Traditional
    1.54
     tradicional
    1.46
     Traditional
    1.38
     tradic
    1.34
    従来
    1.33
     tradisional
    1.24
     traditionelle
    1.23
    Activations Density 0.236%

    No Known Activations