© 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. 22-GEMMASCOPE-RES-131K
    7. 73981
    Prev
    Next
    INDEX
    Explanations

    myths, secrets, and weapons

    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
     to
    -1.35
     porque
    -1.05
    SOUNDBITE
    -1.04
    Rüyada
    -1.00
     diabo
    -0.99
     olarak
    -0.99
     preponder
    -0.98
    5
    -0.98
     intrigu
    -0.96
    BIÉN
    -0.94
    POSITIVE LOGITS
     that
    1.69
     llavero
    1.57
     paño
    1.41
     lámparas
    1.28
     estuche
    1.24
     colchón
    1.23
    Ԫ
    1.19
     bricolaje
    1.17
    jenige
    1.16
     estante
    1.15
    Activations Density 0.007%

    No Known Activations