© 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. 148425
    Prev
    Next
    INDEX
    Explanations

    Australian destination wedding photography

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

    questions and specific terms

    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
    feit
    0.49
    (
    0.49
     invention
    0.47
     enkel
    0.47
     minyak
    0.46
    GE
    0.45
     prevents
    0.45
    ension
    0.45
     advent
    0.45
     ap
    0.44
    POSITIVE LOGITS
    りん
    0.54
     VLC
    0.51
    افل
    0.48
    ﻦ
    0.48
     سپورت
    0.46
     संदेश
    0.46
     کاسینو
    0.45
    ीकरण
    0.45
     Muslim
    0.45
     paso
    0.45
    Activations Density 0.001%

    No Known Activations