© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89922
    Prev
    Next
    INDEX
    Explanations

    options,argscontexterroreventsseedutils

    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_34/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
     equated
    -0.83
     parlement
    -0.82
    üste
    -0.79
     trouvera
    -0.79
     célè
    -0.78
     centru
    -0.78
    ėl
    -0.76
    eeeee
    -0.75
    Lecturer
    -0.75
     アメ
    -0.75
    POSITIVE LOGITS
    miel
    0.81
     particularly
    0.73
    ají
    0.71
     Erlebnis
    0.69
      
    0.69
    ⊶
    0.68
     насеље
    0.67
     ändå
    0.67
     Roster
    0.67
    jections
    0.66
    Activations Density 0.069%

    No Known Activations