© 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. 3228
    Prev
    Next
    INDEX
    Explanations

    key improvements

    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
    Not in Any Lists

    No Comments

    Negative Logits
     possibly
    1.23
     recently
    1.21
     regularmente
    1.20
    に使用
    1.12
     amantes
    1.11
    もしくは
    1.10
    そらく
    1.05
    铃
    1.05
     occasionally
    1.04
     sommige
    1.00
    POSITIVE LOGITS
    outed
    2.30
     機能
    2.29
    gebn
    2.22
     ください
    2.21
    othor
    2.20
     역할을
    2.20
    όν
    2.20
    ijev
    2.19
     Redist
    2.19
    undered
    2.17
    Activations Density 0.021%

    No Known Activations