© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27626
    Prev
    Next
    INDEX
    Explanations

    directions, size, parking, connect, experiences

    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
     will
    -1.75
     it
    -1.63
     get
    -1.49
     could
    -1.45
     bring
    -1.38
     see
    -1.35
     make
    -1.35
     with
    -1.34
     allow
    -1.30
     provides
    -1.28
    POSITIVE LOGITS
    だけではなく
    1.68
     miniaturka
    1.61
     وليس
    1.58
     meubles
    1.58
     triko
    1.57
     rajut
    1.55
     fidé
    1.52
     atlet
    1.46
    だけでなく
    1.45
     vixion
    1.45
    Activations Density 0.082%

    No Known Activations