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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3586
    Prev
    Next
    INDEX
    Explanations

    driving verbs

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

    hard drive and driving verbs

    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
    гти
    0.43
    StripMenuItem
    0.37
    ﻢ
    0.35
    ostęp
    0.35
     পাতা
    0.35
    lesque
    0.34
     Comercio
    0.33
    鉐
    0.32
    ائن
    0.32
     Aerospace
    0.32
    POSITIVE LOGITS
     driving
    4.34
     Driving
    4.09
    Driving
    4.09
    driving
    4.06
    驱动
    4.00
     drive
    3.81
     drove
    3.73
     drives
    3.72
     driv
    3.69
     ड्राइव
    3.64
    Activations Density 0.492%

    No Known Activations