© 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. 86550
    Prev
    Next
    INDEX
    Explanations

    human rights problems

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

    medical, geographic, and factual terms

    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
     Silverstone
    0.46
    notepad
    0.43
    :
    0.42
     Painting
    0.41
     mrt
    0.41
    ماء
    0.41
    bol
    0.41
     CuO
    0.41
    mart
    0.41
    僖
    0.40
    POSITIVE LOGITS
     నే
    0.54
    amaya
    0.49
     tastefully
    0.48
     एक्सेस
    0.48
    నున్న
    0.47
     தனது
    0.47
     quantized
    0.46
     predominantly
    0.46
     तेलु
    0.46
     इन
    0.45
    Activations Density 0.001%

    No Known Activations