© 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. 34-GEMMASCOPE-RES-131K
    7. 65993
    Prev
    Next
    INDEX
    Explanations

    explain, help, or tips

    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_34/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
     rất
    -1.20
     매우
    -1.17
     foarte
    -1.16
     très
    -1.07
     very
    -1.07
     muito
    -1.05
     molto
    -1.05
     bardzo
    -1.04
     VERY
    -1.00
    かなり
    -0.98
    POSITIVE LOGITS
     first
    1.22
     slowly
    1.22
     tomorrow
    1.03
    后再
    0.98
    看看
    0.95
    慢慢
    0.95
     when
    0.93
    āci
    0.92
    Maybe
    0.90
     вместе
    0.90
    Activations Density 0.004%

    No Known Activations