© 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. 154126
    Prev
    Next
    INDEX
    Explanations

    difference between

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

    describing effects, dependencies, or processes

    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
     biosynthesis
    0.52
    Muito
    0.48
     preko
    0.48
     culminating
    0.46
     ক্রমা
    0.46
     بڑھ
    0.46
     evo
    0.45
    ﺐ
    0.45
     nhắn
    0.45
     pesquisa
    0.44
    POSITIVE LOGITS
    ingt
    0.49
    ie
    0.49
    iw
    0.48
    lectricité
    0.48
    dock
    0.47
    д
    0.47
    ih
    0.46
    ewalk
    0.46
    end
    0.46
    üdis
    0.46
    Activations Density 0.001%

    No Known Activations