© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10594
    Prev
    Next
    INDEX
    Explanations

    makeup artist or shop

    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_7_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
    靂
    2.48
    aneamente
    2.43
    ণিত
    2.38
    ds
    2.37
    aneity
    2.24
    kých
    2.24
    ką
    2.19
    owość
    2.17
    躇
    2.16
    鹉
    2.15
    POSITIVE LOGITS
    
    2.33
    〉
    2.20
    𝕀
    2.12
    </sup>
    2.06
     Co
    2.03
     उद्या
    2.00
     √
    1.99
    ्‍य
    1.99
    ୀ
    1.99
     ]),
    1.99
    Activations Density 0.013%

    No Known Activations