© 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. 84398
    Prev
    Next
    INDEX
    Explanations

    includes or besides

    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
     something
    -1.14
     all
    -1.03
     a
    -0.92
    全て
    -0.92
    所有
    -0.85
     and
    -0.85
     dzien
    -0.84
     проблема
    -0.82
     dirigentes
    -0.82
     когда
    -0.81
    POSITIVE LOGITS
     includes
    1.59
     include
    1.23
     Ngoài
    1.14
     besides
    1.06
    ladolid
    1.05
     incluyen
    1.04
     Includes
    0.98
     بيها
    0.98
     will
    0.97
    nymi
    0.94
    Activations Density 0.084%

    No Known Activations