© 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. 129594
    Prev
    Next
    INDEX
    Explanations

    see the

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

    Spanish and Russian words

    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
    用
    0.54
    ísk
    0.52
    可以用
    0.46
    可以
    0.46
     用于
    0.46
     時
    0.46
     haszn
    0.46
     удобно
    0.45
     做
    0.45
     assistive
    0.45
    POSITIVE LOGITS
    ciudad
    0.59
     Gobierno
    0.51
    tarea
    0.50
     Bem
    0.49
    Walter
    0.48
    поли
    0.48
     Karl
    0.48
    सरकार
    0.48
     Walter
    0.47
    ॉर्क
    0.47
    Activations Density 0.002%

    No Known Activations