© 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. 108966
    Prev
    Next
    INDEX
    Explanations

    legal and HR updates

    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
    Precalculus
    -0.82
    mostrar
    -0.80
    Биография
    -0.77
    Gaia
    -0.77
    énom
    -0.77
     offiziellen
    -0.75
    📷
    -0.75
     tatuagens
    -0.74
    Science
    -0.74
    شاه
    -0.73
    POSITIVE LOGITS
     compliance
    1.38
     updates
    1.34
     update
    1.27
     legal
    1.22
     alert
    1.17
     seminar
    1.17
     webinar
    1.13
     practical
    1.13
     Legal
    1.12
     regulatory
    1.12
    Activations Density 0.067%

    No Known Activations