© 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. 1124
    Prev
    Next
    INDEX
    Explanations

    adjective/adverb followed by noun/comparative

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

    sin embargo

    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
    емого
    0.30
    asionally
    0.30
    ruari
    0.28
     keV
    0.28
    راً
    0.27
    仑
    0.27
    ྛ
    0.27
     sulphate
    0.27
    られて
    0.27
    꼐
    0.27
    POSITIVE LOGITS
    cou
    0.30
    christian
    0.26
     Victim
    0.26
     Επι
    0.25
     Erdogan
    0.25
    ড্রিম
    0.25
    কাশ
    0.25
    ingin
    0.25
    tomcat
    0.25
    ardi
    0.24
    Activations Density 0.184%

    No Known Activations