© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98565
    Prev
    Next
    INDEX
    Explanations

    iterator, self, consumed, values

    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_22/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
     your
    -1.56
    Nhan
    -1.05
    Quy
    -1.05
    řel
    -0.98
    ATIVA
    -0.97
     созда
    -0.96
     membangun
    -0.95
    ıyoruz
    -0.94
     creador
    -0.94
     you
    -0.94
    POSITIVE LOGITS
     spiaggia
    0.99
    mazoo
    0.87
     recherches
    0.85
    だか
    0.83
    するか
    0.82
    ert
    0.82
     carnage
    0.81
     there
    0.81
    되
    0.80
    isatie
    0.80
    Activations Density 0.005%

    No Known Activations