© 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. 99814
    Prev
    Next
    INDEX
    Explanations

    called apply

    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
     Burnham
    -0.93
    जन
    -0.76
     verheir
    -0.74
     rides
    -0.74
    سكرية
    -0.71
     сын
    -0.71
     undersigned
    -0.70
    指揮
    -0.69
     erwartet
    -0.69
    ZT
    -0.69
    POSITIVE LOGITS
     ajang
    0.77
     down
    0.75
     Jungle
    0.75
    煥
    0.73
    =]
    0.72
    down
    0.72
    mons
    0.72
    MONS
    0.71
    bru
    0.70
    Enums
    0.70
    Activations Density 0.003%

    No Known Activations