© 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. 34-GEMMASCOPE-RES-131K
    7. 63535
    Prev
    Next
    INDEX
    Explanations

    shift register circuits

    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
     glabrous
    -0.81
    lagte
    -0.73
    Fork
    -0.71
     Fland
    -0.71
    はな
    -0.71
     algu
    -0.71
    DataService
    -0.70
    呜呜
    -0.69
    دى
    -0.68
    чкой
    -0.67
    POSITIVE LOGITS
     shift
    1.44
     Shift
    1.27
    Shift
    1.16
     register
    1.14
     LF
    1.09
     Register
    1.04
     registers
    1.03
    シフト
    0.97
    shift
    0.97
    Register
    0.97
    Activations Density 0.059%

    No Known Activations