© 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. 12-GEMMASCOPE-2-RES-16K
    7. 3110
    Prev
    Next
    INDEX
    Explanations

    is key or essential

    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_12_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
    ritable
    1.91
    愁
    1.81
    ăți
    1.76
     dość
    1.75
    引起的
    1.74
    стта
    1.72
    特徴
    1.72
    룸
    1.72
    沌
    1.71
     geralmente
    1.70
    POSITIVE LOGITS
     crown
    1.30
     payoff
    1.24
     Honor
    1.21
     Trif
    1.21
     victory
    1.20
     recomp
    1.18
     gold
    1.16
     priority
    1.16
     bonus
    1.16
     priceless
    1.15
    Activations Density 0.290%

    No Known Activations