© 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. 469
    Prev
    Next
    INDEX
    Explanations

    currency, specific terms

    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
     encourage
    -0.90
     every
    -0.85
     out
    -0.84
     struggling
    -0.82
     perhaps
    -0.82
     at
    -0.82
     found
    -0.81
     there
    -0.81
     just
    -0.81
     after
    -0.81
    POSITIVE LOGITS
    used
    1.09
     uży
    0.89
     NEEDS
    0.88
     usado
    0.88
     различ
    0.87
     usada
    0.87
    
    0.86
    played
    0.86
     insanely
    0.86
     sidste
    0.85
    Activations Density 0.020%

    No Known Activations