© 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. 80002
    Prev
    Next
    INDEX
    Explanations

    quotes and questions

    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
     Tél
    -1.24
    omorphisms
    -1.16
    ಱ
    -1.13
    ほら
    -1.12
    imanapun
    -1.10
     beleid
    -1.09
     bús
    -1.09
    май
    -1.08
     Février
    -1.07
    BindingResult
    -1.06
    POSITIVE LOGITS
     and
    1.05
     Ortsteil
    1.02
     but
    1.00
     additional
    0.98
     inability
    0.95
    </h2>
    0.93
     Lainnya
    0.92
    漣
    0.91
     Latein
    0.90
     still
    0.90
    Activations Density 0.000%

    No Known Activations