© 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. 22-GEMMASCOPE-RES-131K
    7. 54514
    Prev
    Next
    INDEX
    Explanations

    month and year updates

    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
     uitges
    -1.06
     orquí
    -1.05
    Carex
    -1.04
    cheiben
    -1.02
    føring
    -0.99
     titulo
    -0.97
     moeilijk
    -0.96
    btnLogin
    -0.96
     veya
    -0.95
     refrigerador
    -0.95
    POSITIVE LOGITS
     update
    1.04
     updated
    1.02
     by
    1.02
     changes
    0.98
     latest
    0.96
    を入れて
    0.94
     updates
    0.93
    update
    0.91
    updated
    0.91
    add
    0.90
    Activations Density 0.034%

    No Known Activations