© 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. 84032
    Prev
    Next
    INDEX
    Explanations

    live match score

    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
     this
    -1.20
     each
    -0.91
     what
    -0.88
     within
    -0.88
     some
    -0.87
     typically
    -0.85
     by
    -0.84
     protect
    -0.83
    CORRE
    -0.78
    ėjas
    -0.78
    POSITIVE LOGITS
     FOLLOW
    1.04
    чок
    0.97
    ütt
    0.93
     لكم
    0.91
    гать
    0.89
     adresu
    0.88
    看见
    0.85
    krä
    0.84
     eenen
    0.84
     própri
    0.83
    Activations Density 0.008%

    No Known Activations