© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92058
    Prev
    Next
    INDEX
    Explanations

    setting target values

    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
    Vente
    -0.77
    Solución
    -0.75
    钥匙
    -0.73
    ליך
    -0.71
    宍
    -0.71
     experimento
    -0.70
    だけは
    -0.69
    already
    -0.68
    Enlight
    -0.68
    INTRODUCCIÓN
    -0.68
    POSITIVE LOGITS
     target
    2.19
    Target
    1.86
     commanded
    1.80
     command
    1.79
    target
    1.78
     desired
    1.72
     Target
    1.70
     set
    1.70
     reference
    1.65
     commands
    1.64
    Activations Density 0.047%

    No Known Activations