© 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. 176805
    Prev
    Next
    INDEX
    Explanations

    specific nouns and following words

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

    list data labels

    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
     Überblick
    0.48
     Auswahl
    0.48
    ية
    0.48
    ługa
    0.48
    ب
    0.47
     Annals
    0.47
     Italien
    0.47
     Itália
    0.47
    enka
    0.45
    هِ
    0.44
    POSITIVE LOGITS
    ក៏
    0.58
     cloudinary
    0.48
     enclose
    0.45
     przeciw
    0.45
     shear
    0.44
     конструкции
    0.44
    edil
    0.43
    畠
    0.42
     सिलेंडर
    0.42
     конструк
    0.42
    Activations Density 0.000%

    No Known Activations