© 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. 98615
    Prev
    Next
    INDEX
    Explanations

    tiltrotor, Crete, media, Q:

    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
     Realism
    -0.79
     clergymen
    -0.79
    Azerbaijan
    -0.76
    Azer
    -0.75
    Baku
    -0.75
     lanyard
    -0.75
     devotee
    -0.74
     termasuk
    -0.73
     grins
    -0.72
     behavi
    -0.71
    POSITIVE LOGITS
    ISING
    0.82
     ahí
    0.80
     manquer
    0.79
     Nintendo
    0.76
    lardır
    0.75
     psychiatric
    0.75
     Cake
    0.75
    lccccc
    0.75
     fashion
    0.74
     bracelet
    0.74
    Activations Density 0.006%

    No Known Activations