© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2189
    Prev
    Next
    INDEX
    Explanations

    units of area and volume

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

    mathematical powers and exponents

    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
    ;\;\
    0.40
     !***
    0.39
    
    0.36
    郆
    0.36
     $(*
    0.35
    埥
    0.34
    .$(
    0.34
     createSprite
    0.33
     किंग
    0.33
    )|\
    0.33
    POSITIVE LOGITS
    <sup>
    0.82
    <sub>
    0.71
    ^{
    0.60
    ¹
    0.54
    ²
    0.53
     ${
    0.52
    ³
    0.51
    ₂
    0.50
    ³,
    0.50
    ⁶
    0.50
    Activations Density 0.077%

    No Known Activations