© 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. 76803
    Prev
    Next
    INDEX
    Explanations

    depends on or upon

    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
     pertinentes
    -1.03
    ViewChild
    -1.02
    .*")]
    -1.01
     для
    -0.96
    ärer
    -0.94
     هذا
    -0.94
     proteína
    -0.91
     sementes
    -0.91
     допомогою
    -0.90
     diferentes
    -0.88
    POSITIVE LOGITS
     depends
    1.63
     on
    1.59
     зависит
    1.58
     Depends
    1.48
    取决于
    1.24
     depende
    1.14
    Depends
    1.13
     greatly
    1.13
     factors
    1.12
    很大
    1.11
    Activations Density 0.024%

    No Known Activations