© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4807
    Prev
    Next
    INDEX
    Explanations

    registers and code instructions

    np_acts-logits-general · gemini-2.5-flash-lite

    assembly register operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Waterford
    0.47
    篪
    0.46
    镶
    0.45
    弯
    0.45
    飏
    0.44
    喁
    0.44
     ताम
    0.44
     emuls
    0.43
     Valent
    0.43
     Tjiwarl
    0.41
    POSITIVE LOGITS
    iget
    0.70
    invoke
    0.65
     goto
    0.62
    goto
    0.55
    ->
    0.53
     invoke
    0.52
    locals
    0.50
    monitor
    0.49
    registers
    0.49
     invokes
    0.48
    Activations Density 0.000%

    No Known Activations