© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98582
    Prev
    Next
    INDEX
    Explanations

    census, Living, License

    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
    ohist
    -0.79
    訟
    -0.76
    )}=\
    -0.69
    lanır
    -0.69
     hund
    -0.67
     into
    -0.67
    mtext
    -0.67
    RFC
    -0.66
    )}$.
    -0.65
    ViewInit
    -0.64
    POSITIVE LOGITS
    Perú
    0.81
    ția
    0.77
     skirts
    0.67
     xuân
    0.66
    checkOut
    0.66
    翅
    0.66
    型
    0.65
     Legislature
    0.65
     takım
    0.65
    ommen
    0.64
    Activations Density 0.105%

    No Known Activations