© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 245634
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pdb
    0.52
     ನೀರಿನ
    0.51
    𝒎
    0.50
    𝓭
    0.49
     लाहिड़ी
    0.49
    하루
    0.48
    avasena
    0.48
    の後
    0.48
     सॉल्यू
    0.47
    ́ch
    0.47
    POSITIVE LOGITS
     disillusion
    0.43
     unemployment
    0.41
     energetically
    0.41
    бера
    0.40
     Reverend
    0.40
     acquisitions
    0.39
     Рей
    0.39
    ,
    0.39
     subsid
    0.39
     indef
    0.39
    Activations Density 0.001%

    No Known Activations