© 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. 25947
    Prev
    Next
    INDEX
    Explanations

    proposed novel methods

    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
     anunció
    -1.31
     dilaporkan
    -1.25
     mengumumkan
    -1.10
    tą
    -1.08
     confirmó
    -1.05
    возмо
    -1.00
    tubers
    -1.00
     сын
    -0.98
     sogenannten
    -0.97
    國際
    -0.94
    POSITIVE LOGITS
     our
    1.23
     we
    1.18
     proposed
    1.05
    MatInputModule
    1.03
    ac
    1.03
     الجديد
    1.01
     herein
    0.97
    new
    0.97
     $
    0.96
     novel
    0.96
    Activations Density 0.020%

    No Known Activations