© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8291
    Prev
    Next
    INDEX
    Explanations

    educational platforms and subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
     Xuan
    0.98
    𝑵
    0.94
    рт
    0.92
     Megh
    0.91
     Nang
    0.90
    ційний
    0.90
    charset
    0.89
     NH
    0.89
     сх
    0.88
     Php
    0.88
    POSITIVE LOGITS
    leye
    1.12
     wọn
    1.06
     ṣe
    1.06
     awọn
    1.05
    oyin
    1.04
     ẹ
    1.04
    olu
    1.03
    pele
    1.02
     Ade
    1.02
    agun
    1.00
    Activations Density 0.043%

    No Known Activations