© 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. 173560
    Prev
    Next
    INDEX
    Explanations

    business and descriptive terms

    np_acts-logits-general · gemini-2.5-flash-lite

    weeks, effort, impact

    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
     ανθρώ
    0.50
    protect
    0.49
    举报
    0.49
    줬
    0.47
    ニチイ
    0.46
     Nası
    0.46
    èmes
    0.46
    对着
    0.46
    opub
    0.46
    까
    0.46
    POSITIVE LOGITS
     لكل
    0.50
     semana
    0.46
     weeks
    0.45
     Weeks
    0.45
    ↵
    0.44
     wicked
    0.44
     deste
    0.44
     rejuvenate
    0.43
    ويس
    0.43
     sient
    0.43
    Activations Density 0.000%

    No Known Activations