© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13250
    Prev
    Next
    INDEX
    Explanations

    dual-channel, Each Use, getElementById, used to, our Vitamin

    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_13_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
    력
    1.48
    력을
    1.28
     tissue
    1.26
    텨
    1.25
    тить
    1.20
    力和
    1.19
    ärke
    1.16
    렵
    1.16
    णू
    1.16
    ීර
    1.15
    POSITIVE LOGITS
     }}"
    1.45
    Atlant
    1.45
    ֙
    1.43
    vět
    1.42
    しまった
    1.40
    Ali
    1.39
     മുഹമ്മ
    1.39
    ؔ
    1.37
    PAC
    1.37
    Quran
    1.36
    Activations Density 0.000%

    No Known Activations