© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2193
    Prev
    Next
    INDEX
    Explanations

    heavy equipment and appliances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     spotify
    1.93
     mixtape
    1.84
    Pinterest
    1.82
    Spotify
    1.75
     Spotify
    1.72
     Binance
    1.70
    媛
    1.67
    ガチャ
    1.66
     SoundCloud
    1.66
     Gambling
    1.64
    POSITIVE LOGITS
     tractors
    1.72
     efficiencies
    1.71
     forklift
    1.70
    advantages
    1.69
     ease
    1.68
     vans
    1.68
    兼用
    1.68
    噸
    1.68
     versatile
    1.63
     advantage
    1.62
    Activations Density 0.081%

    No Known Activations