© 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. 223790
    Prev
    Next
    INDEX
    Explanations

    non-Latin scripts

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

    understanding and navigating lists

    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
     samot
    0.54
    en
    0.52
    奮
    0.50
    anu
    0.49
    é
    0.49
    click
    0.48
    ack
    0.48
    2
    0.47
    aka
    0.47
    ovable
    0.47
    POSITIVE LOGITS
     চৈতন্ত
    0.54
     antérieure
    0.51
     চিং
    0.50
     rameaux
    0.49
    ື່ອ
    0.48
    饷
    0.47
    嵐
    0.46
    চৈত
    0.46
    ﻞ
    0.45
     musicales
    0.45
    Activations Density 0.001%

    No Known Activations