© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22882
    Prev
    Next
    INDEX
    Explanations

    all words}

    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
     akár
    0.47
     parfois
    0.45
     মতো
    0.45
    简单
    0.44
     leveraging
    0.44
     /ˈ
    0.43
    ໌
    0.43
     meskipun
    0.42
     simply
    0.42
    ​
    0.41
    POSITIVE LOGITS
     wszystkie
    0.58
     всіх
    0.57
     ಎಲ್ಲಾ
    0.54
    全ての
    0.54
     tutte
    0.53
     அனைத்து
    0.53
    すべての
    0.52
     всички
    0.51
     모든
    0.51
     wszystkich
    0.51
    Activations Density 0.095%

    No Known Activations