© 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. 229554
    Prev
    Next
    INDEX
    Explanations

    nor adulterers

    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
    ဏ
    0.46
    стен
    0.45
    都有
    0.45
    MsgCallBack
    0.45
     पोस्टम
    0.45
    ли
    0.44
    用語
    0.44
    ők
    0.43
    தி
    0.43
    Texture
    0.43
    POSITIVE LOGITS
     journe
    0.54
     kuma
    0.50
     nays
    0.48
    ዱ
    0.48
     Evet
    0.46
     Kamu
    0.46
     rotate
    0.45
     busiest
    0.45
     encompassed
    0.45
     Situs
    0.44
    Activations Density 0.000%

    No Known Activations