© 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. 22-GEMMASCOPE-RES-131K
    7. 67373
    Prev
    Next
    INDEX
    Explanations

    so ... that

    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
     these
    -1.17
     estados
    -1.08
     secado
    -0.99
     hábit
    -0.99
     hombros
    -0.98
    圌
    -0.98
     Autres
    -0.96
    opheles
    -0.95
     manguera
    -0.94
     emisiones
    -0.94
    POSITIVE LOGITS
     even
    1.68
     sogar
    1.61
     bahkan
    1.56
     zelfs
    1.56
    甚至
    1.53
     навіть
    1.53
     perhaps
    1.46
     حتی
    1.40
     даже
    1.38
     incluso
    1.36
    Activations Density 0.036%

    No Known Activations