© 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. 22945
    Prev
    Next
    INDEX
    Explanations

    capabilities, translation, summarization

    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
    КО
    0.52
    ديد
    0.45
    Ги
    0.44
    Фор
    0.43
    Р
    0.43
    킹
    0.43
    Rated
    0.43
    Hosting
    0.42
    กำหนด
    0.42
    COR
    0.40
    POSITIVE LOGITS
     對
    0.53
     vegans
    0.49
     deleniti
    0.46
    gehen
    0.45
    te
    0.45
     Plata
    0.45
     :/
    0.44
     Fehl
    0.43
     nj
    0.43
    ខាង
    0.43
    Activations Density 0.003%

    No Known Activations