© 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. 11136
    Prev
    Next
    INDEX
    Explanations

    code comments or file paths

    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
     like
    -1.29
     from
    -1.13
     for
    -1.08
     you
    -1.05
     would
    -1.03
     blatantly
    -1.00
     only
    -0.98
     undeniably
    -0.98
     truly
    -0.96
    !!!!
    -0.95
    POSITIVE LOGITS
     拆
    1.15
    ראות
    1.05
     deline
    1.04
    Dimens
    0.99
     завер
    0.98
    看你
    0.97
    ומית
    0.97
    completed
    0.97
    returning
    0.95
     devast
    0.94
    Activations Density 0.000%

    No Known Activations