© 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. 34-GEMMASCOPE-RES-131K
    7. 64121
    Prev
    Next
    INDEX
    Explanations

    source to target mappings

    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
    جهة
    -0.85
    These
    -0.83
    冨
    -0.80
    горит
    -0.79
    ziej
    -0.79
     while
    -0.75
     Hobbes
    -0.75
    satin
    -0.75
     grep
    -0.75
    ществ
    -0.75
    POSITIVE LOGITS
     target
    1.70
     source
    1.35
     Target
    1.19
     targets
    1.08
     Source
    1.01
     doel
    0.98
    target
    0.97
     reference
    0.91
     Translation
    0.88
     sources
    0.87
    Activations Density 0.003%

    No Known Activations