© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33979
    Prev
    Next
    INDEX
    Explanations

    bringing back or revival

    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_22/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
     identificar
    -0.86
     schimb
    -0.84
    における
    -0.79
     spacer
    -0.78
     inspecting
    -0.77
     Krise
    -0.77
     первом
    -0.77
    卸载
    -0.76
     dě
    -0.75
     väx
    -0.75
    POSITIVE LOGITS
     old
    1.15
     anciens
    1.00
     ancien
    0.99
    nachron
    0.98
     kembali
    0.98
    旧
    0.97
     anciennes
    0.96
    onResume
    0.95
    UMNS
    0.95
    beit
    0.94
    Activations Density 0.058%

    No Known Activations