© 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. 65353
    Prev
    Next
    INDEX
    Explanations

    through which

    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
     sensational
    -0.86
     allerede
    -0.84
    ándome
    -0.83
     möjlighet
    -0.80
     ameste
    -0.79
     sprzed
    -0.78
    
    -0.77
    Rendez
    -0.77
     McGovern
    -0.75
     caduta
    -0.75
    POSITIVE LOGITS
     Barb
    1.00
    :'#
    0.96
    рослав
    0.80
     PÅ
    0.79
    quê
    0.77
    росла
    0.77
    찮
    0.77
     parlent
    0.77
     ремон
    0.76
     Campus
    0.75
    Activations Density 0.039%

    No Known Activations