© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3404
    Prev
    Next
    INDEX
    Explanations

    #include <stdio.h>

    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
    mz
    1.06
    слу
    1.04
    เข้ามา
    0.99
    arrive
    0.99
    ılarak
    0.98
    inen
    0.97
    derive
    0.97
     x
    0.96
     wspól
    0.96
    hidupan
    0.95
    POSITIVE LOGITS
    を開
    1.27
    ljen
    1.23
    앵
    1.23
    chée
    1.22
    を切
    1.21
    devtools
    1.21
    が開
    1.17
    rimer
    1.16
    зей
    1.15
    pendown
    1.13
    Activations Density 0.057%

    No Known Activations