© 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. 119392
    Prev
    Next
    INDEX
    Explanations

    life or lift prefixes

    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
     apartment
    -1.77
     office
    -1.34
     Office
    -1.14
    apartment
    -1.11
     OFFICE
    -1.02
    office
    -0.98
    馀
    -0.88
     Apartment
    -0.85
     Castelo
    -0.83
     Büro
    -0.82
    POSITIVE LOGITS
     Turned
    0.86
    alities
    0.84
    を行い
    0.84
     Mein
    0.83
    isesta
    0.79
    ciendo
    0.79
    もうすぐ
    0.79
    みたいに
    0.78
    を行います
    0.77
    ?*
    0.77
    Activations Density 0.245%

    No Known Activations