© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99123
    Prev
    Next
    INDEX
    Explanations

    fight matchups

    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
    pension
    -0.77
     PKK
    -0.77
    砝
    -0.75
    suffix
    -0.74
    NOTA
    -0.74
    tissimo
    -0.72
     Rott
    -0.71
    وم
    -0.71
     Transformers
    -0.70
    国防
    -0.69
    POSITIVE LOGITS
    portable
    0.79
     Saudi
    0.79
    quias
    0.77
     megfelelő
    0.76
    Ә
    0.75
     МВД
    0.75
    dune
    0.75
    冂
    0.75
    popper
    0.73
    🩹
    0.73
    Activations Density 0.010%

    No Known Activations