© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51347
    Prev
    Next
    INDEX
    Explanations

    articles and conjunctions

    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_65k_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
    an
    0.51
    is
    0.48
     посредством
    0.46
    e
    0.46
    и
    0.46
    just
    0.46
    always
    0.45
    o
    0.45
    i
    0.45
    quando
    0.45
    POSITIVE LOGITS
     staircase
    0.56
     chiến
    0.48
    ڑ
    0.44
     brasileiro
    0.43
     염
    0.43
    ังกฤษ
    0.42
     brasileira
    0.42
    分岐
    0.42
     bactéries
    0.41
     acidification
    0.40
    Activations Density 0.030%

    No Known Activations