© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5305
    Prev
    Next
    INDEX
    Explanations

    multilingual items paired

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    อง
    1.19
    Authorities
    1.18
    Continue
    1.14
     animados
    1.11
     toer
    1.07
    </b>
    1.07
    雑誌
    1.07
    Deputy
    1.06
     ascenso
    1.05
     accéder
    1.03
    POSITIVE LOGITS
     بناء
    1.31
    elry
    1.30
    割
    1.27
     fundament
    1.25
    estas
    1.23
     ماده
    1.22
     Azer
    1.21
     underval
    1.21
     ضروری
    1.20
     inherit
    1.19
    Activations Density 0.020%

    No Known Activations