© 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. 22473
    Prev
    Next
    INDEX
    Explanations

    examples such as

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

    specifics of a topic

    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
     a
    0.51
     even
    0.50
      
    0.50
     bond
    0.49
     scenario
    0.48
     sandwich
    0.48
     customer
    0.48
     starter
    0.47
     lump
    0.46
     {
    0.46
    POSITIVE LOGITS
     അതിനാ
    0.52
     Итали
    0.50
    ŝ
    0.48
    hatiti
    0.48
    গী
    0.47
    omerase
    0.47
    nocześnie
    0.46
     그녀
    0.46
     뛰
    0.46
    쾰
    0.46
    Activations Density 0.000%

    No Known Activations