© 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. 75247
    Prev
    Next
    INDEX
    Explanations

    comparison or preference

    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
     applau
    -1.12
     掛け
    -1.08
     również
    -1.05
    Spez
    -1.05
     depositphotos
    -1.02
    ρια
    -1.02
    جمعیت
    -0.99
    ῃ
    -0.99
     tampa
    -0.98
    Cala
    -0.98
    POSITIVE LOGITS
     than
    4.56
     niż
    1.89
    than
    1.88
     rather
    1.74
     instead
    1.51
     THAN
    1.37
     as
    1.35
     versus
    1.31
    มากกว่า
    1.30
    Than
    1.30
    Activations Density 0.041%

    No Known Activations