© 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. 107744
    Prev
    Next
    INDEX
    Explanations

    easy + descriptor

    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
     suitably
    -1.03
    すごく
    -0.91
    可能です
    -0.90
    𝔬
    -0.87
     grève
    -0.85
    ¹
    -0.84
    骉
    -0.84
    urgency
    -0.84
     deuda
    -0.83
    terscotch
    -0.83
    POSITIVE LOGITS
     breezy
    1.91
     easy
    1.73
    going
    1.62
     Easy
    1.37
    Easy
    1.22
    easy
    1.18
    Going
    1.16
     kolay
    1.14
     access
    1.12
     fáciles
    1.08
    Activations Density 0.025%

    No Known Activations