© 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. 49450
    Prev
    Next
    INDEX
    Explanations

    approval and submission

    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
     Putih
    -0.78
    ('*',
    -0.77
     when
    -0.76
     жаль
    -0.74
     нега
    -0.74
    ;
    -0.73
     continues
    -0.73
    thebibliography
    -0.72
    wsze
    -0.71
     Unlike
    -0.70
    POSITIVE LOGITS
     approval
    1.10
     supervisor
    1.01
     APPROVAL
    0.98
     submitted
    0.98
    approval
    0.98
    Approval
    0.94
    Submitted
    0.94
     signatures
    0.94
     supervisors
    0.94
     Approval
    0.92
    Activations Density 0.005%

    No Known Activations