© 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. 10-GEMMASCOPE-RES-131K
    7. 101712
    Prev
    Next
    INDEX
    Explanations

    because

    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_10/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
    苼
    -2.50
     dando
    -2.16
    ⏑
    -2.13
    mainly
    -2.11
     
    -2.11
    ,;
    -2.06
     spearheaded
    -2.05
     ofte
    -2.03
    mme
    -2.03
     andre
    -1.99
    POSITIVE LOGITS
     because
    2.88
     However
    2.84
     since
    2.84
     Since
    2.75
     from
    2.73
     Because
    2.73
     after
    2.55
     with
    2.55
     while
    2.55
     as
    2.47
    Activations Density 0.035%

    No Known Activations