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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7822
    Prev
    Next
    INDEX
    Explanations

    content lists and classifications

    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_65k_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
    ທີ່ມີ
    0.48
    ட்
    0.47
    Desktop
    0.46
    ηση
    0.45
    ரே
    0.44
    ALL
    0.44
    REPO
    0.43
    𝐪
    0.43
     reminding
    0.43
    ﻔ
    0.43
    POSITIVE LOGITS
     adelante
    0.48
    ла
    0.46
    -
    0.44
    vár
    0.44
     Eighth
    0.44
     Vorder
    0.42
     Brus
    0.41
     Yus
    0.41
     Espírito
    0.41
     개의
    0.40
    Activations Density 0.001%

    No Known Activations