© 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. 2300
    Prev
    Next
    INDEX
    Explanations

    variable assignments in code

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

    assignment 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
    <unused48>
    0.57
     থাকিত
    0.54
    <unused44>
    0.53
     অতএব
    0.52
     করিতেছে
    0.51
    <unused32>
    0.51
    <unused26>
    0.50
    ।...
    0.50
     তথাপি
    0.49
    ╿
    0.48
    POSITIVE LOGITS
     =
    2.13
     =(
    1.31
    =
    1.19
     :=
    1.16
     =\
    1.13
    =((
    1.09
     =[
    1.09
    =(
    1.05
    ="";
    1.03
     =&
    1.02
    Activations Density 0.004%

    No Known Activations