© 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. 64684
    Prev
    Next
    INDEX
    Explanations

    "NED Podcast"

    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
     palestra
    -1.02
     Màu
    -0.96
     accolades
    -0.94
     deres
    -0.94
     Accra
    -0.93
     Hauteur
    -0.93
     filha
    -0.93
     datum
    -0.92
    jaard
    -0.91
    Apesar
    -0.91
    POSITIVE LOGITS
     поэтому
    1.00
     berpeng
    0.96
    譴
    0.95
    wijze
    0.93
     membahas
    0.90
     dinilai
    0.88
     älskar
    0.88
     '/')
    0.87
    wertig
    0.86
     from
    0.85
    Activations Density 0.001%

    No Known Activations