© 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. 54182
    Prev
    Next
    INDEX
    Explanations

    after ' by , or

    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
    sierung
    -1.23
    tômes
    -1.13
     différentes
    -1.11
    Paperback
    -1.10
    PARTS
    -1.06
    桄
    -1.05
    Literary
    -0.98
     ___________
    -0.97
     beleid
    -0.97
    ctivo
    -0.96
    POSITIVE LOGITS
     after
    1.14
     always
    1.14
    дцать
    1.11
    '
    1.11
     with
    1.10
     With
    1.08
     not
    1.07
     comes
    1.05
     principally
    1.05
     still
    1.04
    Activations Density 0.237%

    No Known Activations