© 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-262K
    7. 28729
    Prev
    Next
    INDEX
    Explanations

    prohibiting explicit content

    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
     so
    0.40
     -(
    0.40
     which
    0.37
     when
    0.36
     tath
    0.36
     cuando
    0.35
     如何
    0.35
     مثل
    0.35
     然后
    0.35
     quando
    0.34
    POSITIVE LOGITS
    Е
    0.37
     дет
    0.36
     молодо
    0.35
    不仅
    0.35
     besteht
    0.35
    aksanaan
    0.34
    ру
    0.33
    lovak
    0.33
    tał
    0.33
     состоит
    0.33
    Activations Density 0.018%

    No Known Activations