© 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. 34-GEMMASCOPE-RES-131K
    7. 53811
    Prev
    Next
    INDEX
    Explanations

    ages and years

    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_34/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
    toLocale
    -0.79
    Tanggal
    -0.77
     dát
    -0.76
    ebly
    -0.75
    itudine
    -0.72
     SPE
    -0.71
    krivelse
    -0.69
    ilitary
    -0.69
    gnancy
    -0.69
    sandwich
    -0.69
    POSITIVE LOGITS
     something
    2.63
    something
    2.48
    Something
    2.08
     Something
    2.03
     SOMETHING
    1.70
     qualcosa
    1.55
     somethin
    1.42
    何か
    1.41
     sesuatu
    1.26
    SOM
    1.25
    Activations Density 0.047%

    No Known Activations