© 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. 129994
    Prev
    Next
    INDEX
    Explanations

    waking up feeling something

    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
    handleError
    -1.05
     による
    -0.99
     class
    -0.93
    Radar
    -0.93
    érêt
    -0.93
     they
    -0.91
    巴巴
    -0.91
    mē
    -0.91
     client
    -0.91
     risk
    -0.91
    POSITIVE LOGITS
     memories
    1.30
    ßten
    1.12
     amnesia
    1.09
     surroundings
    1.07
     kroppen
    1.04
    ßte
    1.00
    りましたが
    0.99
     steder
    0.98
     cintur
    0.97
    りますが
    0.96
    Activations Density 0.021%

    No Known Activations