© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7136
    Prev
    Next
    INDEX
    Explanations

    introducing the purpose of a text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    strated
    2.20
    toprule
    2.18
     √(
    2.07
    뉜
    2.04
     isp
    2.00
     }}=\
    2.00
     (†
    2.00
    clu
    2.00
    뉩
    1.99
    anden
    1.98
    POSITIVE LOGITS
    Purpose
    1.66
    Aim
    1.52
    目的
    1.45
     PURPOSE
    1.43
     Purpose
    1.43
     purpose
    1.38
    Objectives
    1.35
     objetivo
    1.34
    Objective
    1.30
     aim
    1.28
    Activations Density 0.028%

    No Known Activations