© 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. 178867
    Prev
    Next
    INDEX
    Explanations

    locations, names, and specific entities

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

    attention, field, reports, work

    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
     d
    0.46
     °
    0.45
     така
    0.45
     значительно
    0.45
     u
    0.45
     r
    0.44
     v
    0.44
     xuất
    0.43
     rada
    0.43
     nettement
    0.42
    POSITIVE LOGITS
    Austria
    0.54
     городской
    0.49
    Qatar
    0.48
    bollywood
    0.48
    が通販
    0.48
    ნის
    0.47
     Alexei
    0.47
    캘
    0.47
    Indonesia
    0.46
    Poland
    0.46
    Activations Density 0.001%

    No Known Activations