© 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. 224280
    Prev
    Next
    INDEX
    Explanations

    numbers and financial figures

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

    adding specific details

    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
     불안
    0.59
     säger
    0.54
     조건
    0.52
    愠
    0.52
    当下
    0.50
     керу
    0.50
     dersimizde
    0.50
     sogen
    0.49
     উত্তেজনা
    0.49
     olarak
    0.49
    POSITIVE LOGITS
    ᱖
    0.40
     concent
    0.38
     compar
    0.38
     replacements
    0.38
     repurchase
    0.38
     loan
    0.38
     refined
    0.38
    细
    0.37
     yearly
    0.37
     femin
    0.37
    Activations Density 0.001%

    No Known Activations