© 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. 249855
    Prev
    Next
    INDEX
    Explanations

    mining sectors

    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
     Расійскай
    0.51
    ęp
    0.50
    하다고
    0.49
    하여
    0.48
     नारायण
    0.47
     insurers
    0.46
    ᒋ
    0.46
    하지
    0.46
    ㅀ
    0.46
    ಿಸ
    0.45
    POSITIVE LOGITS
     mostra
    0.47
    紅色
    0.46
    鈕
    0.46
    0.46
     alcan
    0.45
     biblioteca
    0.45
     presenta
    0.44
    }-${
    0.44
    红色
    0.43
     musica
    0.42
    Activations Density 0.000%

    No Known Activations