© 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. 98698
    Prev
    Next
    INDEX
    Explanations

    past events

    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
     Twice
    -1.07
    rdoba
    -1.05
    senz
    -1.04
     selama
    -1.02
     its
    -1.02
    <u>
    -1.02
    тий
    -1.02
    ↵
    -1.02
     my
    -1.01
    Twice
    -1.00
    POSITIVE LOGITS
     several
    2.05
     two
    1.98
     five
    1.89
     three
    1.88
     about
    1.82
     beberapa
    1.80
     four
    1.74
     Beberapa
    1.70
     några
    1.63
     eight
    1.63
    Activations Density 0.113%

    No Known Activations