© 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. 158536
    Prev
    Next
    INDEX
    Explanations

    if you are going to

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

    if you must

    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
     نداشت
    0.49
     นั่น
    0.44
    굶
    0.44
     হয়নি
    0.42
    stellen
    0.42
     이게
    0.42
    knopf
    0.42
     наоборот
    0.41
    Surprisingly
    0.41
     걱
    0.41
    POSITIVE LOGITS
    一定要
    0.64
     must
    0.57
     MUST
    0.57
    打算
    0.55
     intending
    0.54
     doivent
    0.50
    要注意
    0.50
     unavoidable
    0.50
     phải
    0.49
     moet
    0.48
    Activations Density 0.138%

    No Known Activations