© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 250317
    Prev
    Next
    INDEX
    Explanations

    political or international affairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     тим
    0.47
    arange
    0.45
     Kirkland
    0.45
     Sumb
    0.44
    죽
    0.44
     innumerable
    0.44
     Endpoint
    0.43
     Infinix
    0.43
     Monster
    0.43
     మరియు
    0.42
    POSITIVE LOGITS
    ստ
    0.54
    日內
    0.47
    ਿ
    0.44
    Czech
    0.44
    Օ
    0.44
    ISE
    0.44
     stanu
    0.43
    Politics
    0.43
     suhu
    0.42
    EY
    0.42
    Activations Density 0.000%

    No Known Activations