© 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. 22-GEMMASCOPE-RES-131K
    4. 36129
    Prev
    Next
    INDEX
    Explanations

    digit sequences with hyphens

    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
    JHEP
    -1.09
    читал
    -0.92
    aard
    -0.88
     miljoen
    -0.87
     graduation
    -0.87
    alaska
    -0.86
    alberto
    -0.85
    cuno
    -0.82
     či
    -0.82
     bagi
    -0.82
    POSITIVE LOGITS
     afterwards
    1.07
     remun
    1.05
     later
    1.02
     synthesizer
    1.00
    vitational
    0.99
     cinquième
    0.98
     ulter
    0.97
     mesmos
    0.96
    äki
    0.96
     riuscito
    0.95
    Activations Density 0.006%

    No Known Activations