© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51853
    Prev
    Next
    INDEX
    Explanations

    scatter plot

    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
    亞
    0.49
    ா
    0.49
    ಾ
    0.48
    ە
    0.48
    涀
    0.46
    ྵ
    0.44
     পশ্চিমে
    0.43
    ி
    0.43
     मुस्
    0.43
    эф
    0.43
    POSITIVE LOGITS
     最高
    0.42
    必需
    0.41
    len
    0.40
     gesamte
    0.40
     hangout
    0.40
     entire
    0.40
    抓住
    0.40
     paycheck
    0.39
     pair
    0.39
    तेक
    0.39
    Activations Density 0.007%

    No Known Activations