© 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. 13300
    Prev
    Next
    INDEX
    Explanations

    Nicholas Channel, Interlimb, The properties

    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
     with
    -1.20
     which
    -1.09
     in
    -1.06
     by
    -1.02
     θα
    -0.99
     this
    -0.96
     líqu
    -0.94
     Both
    -0.94
     intense
    -0.94
     information
    -0.93
    POSITIVE LOGITS
     उसके
    1.12
     américains
    1.08
     duradero
    1.04
     certaines
    1.02
     mentre
    1.01
     segunda
    1.01
     обнаружи
    0.99
     cálido
    0.99
    cticut
    0.98
     lijkt
    0.98
    Activations Density 0.001%

    No Known Activations