© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7417
    Prev
    Next
    INDEX
    Explanations

    tailor and refine

    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_22_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
    お
    2.43
    การ
    1.83
    人
    1.82
    一
    1.60
    大
    1.56
    お金
    1.54
    是
    1.40
    お客
    1.37
    大脑
    1.37
     el
    1.36
    POSITIVE LOGITS
    ほうが
    1.36
    ようです
    1.22
    那个
    1.15
     inmediato
    1.13
    这一
    1.12
    這一
    1.06
    ようで
    1.05
    ようだ
    1.04
     través
    1.04
     cias
    1.01
    Activations Density 0.007%

    No Known Activations