© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26657
    Prev
    Next
    INDEX
    Explanations

    auto or automatic settings

    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
    Undergraduate
    -1.00
    ajout
    -0.98
    黩
    -0.96
    镀
    -0.96
    Afternoon
    -0.96
    ьере
    -0.95
     إس
    -0.95
     établissements
    -0.94
    atán
    -0.94
    שמי
    -0.94
    POSITIVE LOGITS
     or
    1.57
     automatic
    1.51
     自动
    1.30
     automatically
    1.24
     Automatic
    1.14
    自动
    1.12
     automatique
    1.08
     автомати
    1.05
     algorithm
    1.05
     which
    1.03
    Activations Density 0.038%

    No Known Activations