© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83945
    Prev
    Next
    INDEX
    Explanations

    legal references

    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
     отношении
    -0.71
     controversy
    -0.71
     stem
    -0.68
    VISED
    -0.67
    бель
    -0.67
     hcm
    -0.66
     anklicken
    -0.66
     GM
    -0.65
    ätten
    -0.65
    OFFICIAL
    -0.65
    POSITIVE LOGITS
     Section
    2.05
    Section
    1.97
     Sections
    1.67
     section
    1.48
     sections
    1.37
     Article
    1.34
    Sections
    1.31
    SECTION
    1.28
    sections
    1.27
    InSection
    1.26
    Activations Density 0.040%

    No Known Activations