© 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. 8608
    Prev
    Next
    INDEX
    Explanations

    size, units, blends, times

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

    is the most common

    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
     consisted
    0.57
     terdiri
    0.56
     gồm
    0.53
     consists
    0.52
     由
    0.52
     consist
    0.49
     began
    0.48
     있던
    0.44
     comenzó
    0.43
    由
    0.43
    POSITIVE LOGITS
    才是
    1.48
    是最
    1.39
     seems
    1.16
    の方が
    1.09
    seems
    1.06
     является
    1.04
     deserves
    1.04
    显得
    1.02
     deserve
    1.01
    是很
    1.00
    Activations Density 0.116%

    No Known Activations