© 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. 34-GEMMASCOPE-RES-131K
    7. 94056
    Prev
    Next
    INDEX
    Explanations

    assembly instructions and registers

    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
    Buona
    -1.07
     incroy
    -1.06
     düğ
    -1.02
    ﻷ
    -1.01
    dolce
    -0.94
     Svizzera
    -0.93
    collana
    -0.91
    roasted
    -0.91
    casque
    -0.91
     città
    -0.90
    POSITIVE LOGITS
     instruction
    1.23
    instruction
    1.06
    Registers
    1.02
    bus
    1.01
     registers
    0.99
     Registers
    0.99
    registers
    0.98
    Instruction
    0.96
    memory
    0.95
    Destination
    0.94
    Activations Density 0.013%

    No Known Activations