© 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. 70822
    Prev
    Next
    INDEX
    Explanations

    more nuanced discussion

    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
    烦
    0.49
     negli
    0.47
     testes
    0.46
     przy
    0.45
     szem
    0.45
    遇到的
    0.44
     impos
    0.44
     Microsc
    0.44
     acum
    0.44
     जेव्हा
    0.44
    POSITIVE LOGITS
    e
    0.57
    l
    0.55
    则
    0.52
    id
    0.52
    or
    0.52
    ore
    0.52
    m
    0.51
    do
    0.50
    like
    0.50
    ie
    0.50
    Activations Density 5.259%

    No Known Activations