© 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. 129880
    Prev
    Next
    INDEX
    Explanations

    fewer characteristics

    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
     signifikan
    -1.10
    sigkeit
    -1.09
     foglie
    -1.08
     rimanere
    -1.07
    kritik
    -1.07
     menurun
    -1.05
    März
    -1.04
    setColumns
    -1.02
     tornare
    -1.02
    esserung
    -1.02
    POSITIVE LOGITS
     they
    1.37
     absence
    1.34
     are
    1.33
    often
    1.27
     lack
    1.24
     require
    1.23
     fewer
    1.20
    Their
    1.19
    usually
    1.17
    ,
    1.16
    Activations Density 0.019%

    No Known Activations