© 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. 165793
    Prev
    Next
    INDEX
    Explanations

    search request

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

    platform, democracy, family, options

    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
    الد
    0.50
    仅仅
    0.49
    宠物
    0.47
    的总
    0.47
    卫生
    0.46
    处于
    0.46
    睁
    0.46
    活动
    0.46
    罚
    0.45
    的时候
    0.45
    POSITIVE LOGITS
    literal
    0.52
     delighted
    0.50
     ricorda
    0.50
    scientists
    0.45
     argued
    0.44
     Lagrangian
    0.44
     necesaria
    0.44
     যুক্তি
    0.44
    Arguments
    0.43
     স্যাম
    0.42
    Activations Density 0.001%

    No Known Activations