© 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. 28347
    Prev
    Next
    INDEX
    Explanations

    code structure

    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
    does
    -2.23
    4
    -2.00
     Konkur
    -1.99
    only
    -1.97
    6
    -1.95
    給你
    -1.89
     diriger
    -1.87
    They
    -1.86
    镡
    -1.84
     klubben
    -1.82
    POSITIVE LOGITS
     in
    1.95
     it
    1.80
     at
    1.80
     cantantes
    1.79
     and
    1.70
     but
    1.66
    になりました
    1.62
     on
    1.59
     supermercados
    1.59
     distritos
    1.55
    Activations Density 0.035%

    No Known Activations