© 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. 129342
    Prev
    Next
    INDEX
    Explanations

    code structure keywords

    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
     to
    -1.23
    するための
    -1.15
     subsequently
    -1.13
    珦
    -1.00
    ributors
    -0.98
     Likewise
    -0.97
    faccia
    -0.97
    Weitere
    -0.94
     рассказать
    -0.94
     Lidé
    -0.93
    POSITIVE LOGITS
     하는
    0.99
    写真は
    0.92
     ejemplo
    0.87
    
    0.86
     solle
    0.86
    掘り
    0.84
     esempio
    0.84
    があり
    0.83
    ه‌اند
    0.83
     прио
    0.83
    Activations Density 0.022%

    No Known Activations