© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10268
    Prev
    Next
    INDEX
    Explanations

    Kyrgyzstan WorkingDirectory

    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_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    u
    2.92
    ゥム
    2.71
    olinium
    2.52
    ו
    2.30
    renergic
    2.29
    有的
    2.26
    ்களை
    2.26
    т
    2.25
    t
    2.24
     drivers
    2.21
    POSITIVE LOGITS
    弾
    2.31
     Freed
    2.22
    ⚐
    2.21
    ільки
    2.19
    ग्रा
    2.18
    idade
    2.14
    郑
    2.10
    နစ်
    2.09
    ernsey
    2.05
     terl
    2.05
    Activations Density 0.014%

    No Known Activations