© 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. 198472
    Prev
    Next
    INDEX
    Explanations

    end of clauses or sentences

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

    states, processes, and outcomes

    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
    errors
    0.55
    ttf
    0.54
    plemented
    0.52
    decyd
    0.49
    {}
    0.49
    isEmpty
    0.49
    =[]
    0.49
    ssa
    0.49
    allele
    0.48
    raf
    0.48
    POSITIVE LOGITS
     Handles
    0.48
     Cardinals
    0.46
     Qualification
    0.46
    면서
    0.45
     Singles
    0.45
     Man
    0.44
     Sellers
    0.44
     Solo
    0.44
     వ
    0.44
     ngoại
    0.44
    Activations Density 0.001%

    No Known Activations