© 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. 72797
    Prev
    Next
    INDEX
    Explanations

    Alternative Characters

    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
    Коммента
    -1.18
     vinilo
    -1.16
     PÅ
    -1.14
     sonre
    -1.09
    Недо
    -1.04
     TÉCNICA
    -1.04
     Keyboard
    -1.03
     erreur
    -0.99
    spotted
    -0.99
    
    -0.97
    POSITIVE LOGITS
     similar
    1.09
     ''
    1.03
     опять
    0.99
    こちらは
    0.98
     Similar
    0.94
     sodass
    0.93
    Again
    0.93
     again
    0.93
     etc
    0.92
     ebbe
    0.92
    Activations Density 0.014%

    No Known Activations