© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 84014
    Prev
    Next
    INDEX
    Explanations

    created timestamps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    嶂
    0.39
    صله
    0.38
     업데이트
    0.38
    ض
    0.38
    _{+}^{
    0.37
    ╅
    0.37
     회
    0.37
    甾
    0.37
    }^{+}
    0.36
    AVAILABLE
    0.36
    POSITIVE LOGITS
     during
    0.48
     durante
    0.44
    tumblr
    0.43
     created
    0.42
     diseñ
    0.41
    mui
    0.40
     Tets
    0.40
     keinginan
    0.40
     cread
    0.40
     Imagen
    0.39
    Activations Density 0.006%

    No Known Activations