© 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. 7204
    Prev
    Next
    INDEX
    Explanations

    sense of purpose, determination, anticipation, energy

    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
     disbursements
    2.02
     telegram
    1.96
     cordial
    1.84
     workmen
    1.84
     messengers
    1.72
     advertiser
    1.72
    encement
    1.70
    romagnet
    1.69
     stimulant
    1.69
    <unused2164>
    1.68
    POSITIVE LOGITS
    )')
    1.31
     liz
    1.23
    )']
    1.19
     Kurulu
    1.19
     õ
    1.19
     '#
    1.18
     бил
    1.15
     Embora
    1.12
     kuf
    1.11
     הבי
    1.10
    Activations Density 0.033%

    No Known Activations