© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50047
    Prev
    Next
    INDEX
    Explanations

    currently, presently, now

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

    remote stations, memory pools, or await connection

    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
    Not in Any Lists

    No Comments

    Negative Logits
    куп
    0.48
    аз
    0.47
    1
    0.45
    че
    0.44
    он
    0.44
    прочем
    0.44
    благо
    0.42
    воль
    0.42
    
    0.41
    клу
    0.41
    POSITIVE LOGITS
     মরু
    0.51
     posee
    0.49
     പരിശോധ
    0.49
     येत
    0.48
     arduous
    0.48
     எல்லோ
    0.48
     આવી
    0.48
     ৭৫
    0.47
     arbeitete
    0.47
     couche
    0.47
    Activations Density 0.001%

    No Known Activations