© 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. 66351
    Prev
    Next
    INDEX
    Explanations

    close to happening

    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
    幸いです
    -1.23
     utilidad
    -1.06
    ментом
    -0.96
    lè
    -0.96
    eley
    -0.93
     flera
    -0.93
    潸
    -0.92
     plusieurs
    -0.90
     praticamente
    -0.90
     Optionen
    -0.87
    POSITIVE LOGITS
     but
    1.41
     when
    1.37
     completely
    1.23
     regarding
    1.17
     what
    1.12
     our
    1.11
     considering
    1.09
     at
    1.09
     because
    1.07
     this
    1.05
    Activations Density 0.037%

    No Known Activations