© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8741
    Prev
    Next
    INDEX
    Explanations

    Russian, Indonesian, Korean, German

    np_acts-logits-general · gemini-2.5-flash-lite

    пожалуйста, умение, применение, поговори

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    𒀀
    0.31
     resection
    0.30
    ர்ஸ்
    0.30
    𝐚
    0.28
    ὤ
    0.28
    之間的
    0.28
    網站
    0.27
     vaisseau
    0.27
    這一
    0.27
    ίσ
    0.27
    POSITIVE LOGITS
    망
    0.26
    큼
    0.26
    략
    0.25
    통
    0.24
    Commissioner
    0.24
     효율
    0.24
    GS
    0.23
    de
    0.23
     каким
    0.23
    ложить
    0.22
    Activations Density 0.014%

    No Known Activations