© 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. 75553
    Prev
    Next
    INDEX
    Explanations

    two words

    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
     fidé
    -1.85
    heiten
    -1.75
    ✁
    -1.73
     sécher
    -1.65
     recev
    -1.61
    Spez
    -1.54
    頭髮
    -1.52
    龇
    -1.52
     interro
    -1.49
     olur
    -1.48
    POSITIVE LOGITS
    \\
    2.25
    _
    2.11
     is
    1.87
     if
    1.83
    </strong>
    1.80
    ?
    1.74
    。
    1.73
     so
    1.71
     two
    1.71
     often
    1.68
    Activations Density 0.120%

    No Known Activations