© 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. 36484
    Prev
    Next
    INDEX
    Explanations

    Punjab will, neural markers, answer questions

    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
     all
    -1.20
     get
    -1.16
     or
    -1.13
     it
    -1.12
     most
    -1.10
     create
    -1.04
     like
    -1.04
    要望
    -1.02
     should
    -1.02
     has
    -1.01
    POSITIVE LOGITS
    ebly
    1.23
    either
    1.22
     indivíduo
    1.16
     despues
    1.15
     دى
    1.14
    ׳
    1.09
     weihnachten
    1.08
    
    1.08
    Anche
    1.05
     SAYS
    1.05
    Activations Density 0.000%

    No Known Activations