© 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. 153310
    Prev
    Next
    INDEX
    Explanations

    Tai Chi

    np_acts-logits-general · gemini-2.5-flash-lite

    don't want to happen

    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
    Ｓ
    0.62
    S
    0.58
    𝐒
    0.52
     ს
    0.52
    𝑠
    0.50
    ース
    0.50
     हेव
    0.50
    g
    0.49
    С
    0.49
    со
    0.49
    POSITIVE LOGITS
     beschrieben
    0.48
     জনগোষ্ঠ
    0.45
     juror
    0.44
     hipótesis
    0.44
    Plaintiffs
    0.43
     ανάπτυ
    0.43
     posY
    0.42
     geograf
    0.41
    ímica
    0.41
     auftreten
    0.41
    Activations Density 0.001%

    No Known Activations