© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14748
    Prev
    Next
    INDEX
    Explanations

    harm and requirements

    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
    Not in Any Lists

    No Comments

    Negative Logits
     池
    1.29
     检测
    1.27
     控制
    1.24
     松
    1.22
     然后
    1.22
     也
    1.22
     病
    1.22
     쉽
    1.22
     是
    1.20
     আরি
    1.20
    POSITIVE LOGITS
     lediglich
    1.16
     múltipl
    1.09
    written
    1.07
     nombreux
    1.06
     dicha
    1.05
     numerosas
    1.05
     compartilh
    1.04
     compartilhar
    1.04
     extremo
    1.04
     gesam
    1.03
    Activations Density 0.000%

    No Known Activations