© 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. 31-GEMMASCOPE-2-RES-262K
    7. 42069
    Prev
    Next
    INDEX
    Explanations

    joining, coming, answering, writing, work

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

    beyond

    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_31_width_262k_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
    ̬
    0.40
     информация
    0.40
     vorhand
    0.39
     збіль
    0.39
    landscape
    0.39
     मानसिकता
    0.38
    同样的
    0.38
    ͚
    0.38
     الداله
    0.37
     Knowledge
    0.37
    POSITIVE LOGITS
    そこ
    0.42
    ETT
    0.41
     corrente
    0.40
    That
    0.39
    ેટ
    0.38
     caza
    0.38
    нул
    0.37
    全く
    0.36
     savoury
    0.35
    鹹
    0.35
    Activations Density 0.059%

    No Known Activations