© 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. 66746
    Prev
    Next
    INDEX
    Explanations

    URLs, code, foreign languages

    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
     mètres
    -0.92
    уна
    -0.90
     bijvoorbeeld
    -0.90
     inkább
    -0.90
    ureusement
    -0.89
     demonstra
    -0.85
     begging
    -0.85
    PropertyChanged
    -0.85
     $[
    -0.85
    ILON
    -0.85
    POSITIVE LOGITS
     to
    0.90
    //----
    0.88
    其他的
    0.87
    //-----
    0.86
    obsolete
    0.85
     приняли
    0.84
     "",
    0.82
     AudioSource
    0.81
     могли
    0.81
     entstanden
    0.81
    Activations Density 0.003%

    No Known Activations