© 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. 50006
    Prev
    Next
    INDEX
    Explanations

    twitter handles

    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
     all
    -0.99
     most
    -0.93
     tamu
    -0.92
     because
    -0.92
     Since
    -0.91
     regardless
    -0.90
     like
    -0.88
     Regardless
    -0.87
     However
    -0.86
    bana
    -0.86
    POSITIVE LOGITS
    #!/
    1.44
     nunc
    1.34
    Its
    1.34
    Actually
    1.19
     реаль
    1.15
    ITHER
    1.15
     réelle
    1.14
    亹
    1.10
    chtet
    1.09
    hashtag
    1.08
    Activations Density 0.027%

    No Known Activations