© 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. 71696
    Prev
    Next
    INDEX
    Explanations

    structural basis for, Q:, FYi, title components

    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
     could
    -1.52
    пью
    -1.45
     to
    -1.45
     only
    -1.38
    Having
    -1.37
    義務
    -1.33
     by
    -1.31
     created
    -1.28
     just
    -1.27
    Just
    -1.27
    POSITIVE LOGITS
     tremendous
    1.49
    ,;
    1.45
     marvelous
    1.41
     gekauft
    1.40
     autén
    1.37
     envejec
    1.35
     secado
    1.35
     magnificent
    1.35
    *;
    1.34
     terrific
    1.31
    Activations Density 0.000%

    No Known Activations