© 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. 112328
    Prev
    Next
    INDEX
    Explanations

    past participial verbs or currency amounts

    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
    かの
    0.46
    .</
    0.45
    ت
    0.44
     manifest
    0.43
    Public
    0.43
    ethod
    0.42
    {$
    0.42
    <?
    0.41
     Survey
    0.40
    Survey
    0.40
    POSITIVE LOGITS
     proteína
    0.50
     deewana
    0.50
     mosque
    0.49
     hookah
    0.49
     oligarch
    0.46
     vucc
    0.45
     kimchi
    0.45
    ভিয়েতনাম
    0.45
    HTTPSampler
    0.44
     ಖರೀದ
    0.44
    Activations Density 0.006%

    No Known Activations