© 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. 14179
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and notation

    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
     that
    -1.79
     by
    -1.56
     which
    -1.55
     in
    -1.55
     using
    -1.44
     semestre
    -1.44
    引言
    -1.39
     from
    -1.34
     before
    -1.34
    ParallelGroup
    -1.33
    POSITIVE LOGITS
    he
    1.68
    on
    1.61
     zweimal
    1.58
     exceptionally
    1.57
    you
    1.57
     unbelievably
    1.52
     myriad
    1.52
     gigantic
    1.50
     immense
    1.50
    six
    1.50
    Activations Density 0.001%

    No Known Activations