© 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. 14102
    Prev
    Next
    INDEX
    Explanations

    who understand or have

    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
     포함
    1.67
     인
    1.67
     한
    1.64
     However
    1.62
    의
    1.61
     모두
    1.57
    들의
    1.55
     的
    1.55
     가장
    1.55
     중
    1.54
    POSITIVE LOGITS
     tragedia
    1.15
     aceite
    1.13
     história
    1.11
     danza
    1.10
     textos
    1.10
     obra
    1.09
    éz
    1.09
     aspecto
    1.08
     país
    1.08
     fase
    1.08
    Activations Density 0.001%

    No Known Activations