© 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. 81186
    Prev
    Next
    INDEX
    Explanations

    a little unusual

    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
     enough
    -1.55
     largely
    -1.45
     hugely
    -1.39
     sooo
    -1.37
     بسیاری
    -1.34
     soooo
    -1.34
     incredibly
    -1.31
     extremely
    -1.29
     vastly
    -1.29
     ترین
    -1.24
    POSITIVE LOGITS
     on
    1.69
     perhaps
    1.48
     might
    1.45
     maybe
    1.45
     each
    1.45
     Maybe
    1.36
    🤏
    1.34
     here
    1.31
     occasionally
    1.31
     if
    1.28
    Activations Density 0.040%

    No Known Activations