© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27777
    Prev
    Next
    INDEX
    Explanations

    composition ofDemand ofmultiple usersfour cavepeople

    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
    ᴢ
    -0.83
    perse
    -0.81
     persona
    -0.79
    řád
    -0.79
    empereur
    -0.78
    razione
    -0.77
    ﹚
    -0.75
     kimse
    -0.75
    裡面
    -0.75
    ONI
    -0.75
    POSITIVE LOGITS
     their
    1.25
    他们在
    0.97
    who
    0.94
     them
    0.94
    给他们
    0.94
     mereka
    0.93
    their
    0.93
    让他们
    0.93
     who
    0.92
     equipment
    0.92
    Activations Density 0.231%

    No Known Activations