© 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. 163669
    Prev
    Next
    INDEX
    Explanations

    phrases completing common structures

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

    listing or describing plans

    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
    咂
    0.54
    在這個
    0.52
    ండె
    0.49
    ANDE
    0.48
     estrange
    0.47
    ܂
    0.47
    ADDED
    0.46
    chec
    0.46
     justamente
    0.45
    ﻘ
    0.45
    POSITIVE LOGITS
    Pumpkin
    0.45
     கண்டி
    0.43
    ಬ್ಬಿಣ
    0.42
     مورد
    0.41
    Coffee
    0.41
     آینده
    0.41
    ჯგუფი
    0.41
     Evening
    0.40
    Ле
    0.39
     Membranes
    0.39
    Activations Density 0.001%

    No Known Activations