© 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. 25928
    Prev
    Next
    INDEX
    Explanations

    multilingual words

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

    specific phrases and their punctuation

    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
     describes
    0.44
    _
    0.43
    ，
    0.43
    称为
    0.42
     called
    0.41
    两个
    0.41
    Cursor
    0.41
     cursorPos
    0.40
     线
    0.40
     branch
    0.39
    POSITIVE LOGITS
     dormir
    0.57
     किंवा
    0.51
     magari
    0.50
     गुस्सा
    0.49
     부담
    0.48
    もしくは
    0.48
     если
    0.48
    結局
    0.47
    然后再
    0.47
     perquè
    0.46
    Activations Density 0.000%

    No Known Activations