© 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. 65600
    Prev
    Next
    INDEX
    Explanations

    states of being or appearing

    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
     cikin
    -0.99
     أنا
    -0.96
     trochu
    -0.95
    Zubereitung
    -0.94
    thello
    -0.93
    ষ্ট
    -0.91
    determin
    -0.90
     papeles
    -0.89
    咾
    -0.88
    Handlung
    -0.87
    POSITIVE LOGITS
     rumored
    1.03
     what
    1.02
     appears
    0.98
     seems
    0.98
     showed
    0.98
     unknown
    0.96
     Parece
    0.95
     owns
    0.94
     strange
    0.94
    呜
    0.93
    Activations Density 0.001%

    No Known Activations