© 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. 40-GEMMASCOPE-2-RES-262K
    7. 213556
    Prev
    Next
    INDEX
    Explanations

    supposed to be, how to, leading to

    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_40_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
     személy
    0.48
    $~
    0.46
     .\
    0.44
     हो
    0.43
     aç
    0.43
     forstå
    0.43
     pregnancies
    0.42
     complained
    0.42
    ǘ
    0.42
     צ
    0.41
    POSITIVE LOGITS
    trigger
    0.37
    tables
    0.37
    dah
    0.37
    довой
    0.37
    kowo
    0.36
    관리
    0.36
    我可以
    0.36
    duty
    0.35
    واز
    0.35
     Pratt
    0.35
    Activations Density 0.001%

    No Known Activations