© 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. 132259
    Prev
    Next
    INDEX
    Explanations

    foreign language classifiers

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

    technically savvy or created by

    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
     対応
    0.44
     遊ん
    0.44
     旧
    0.42
     流
    0.41
     trunks
    0.41
    每月
    0.41
     色
    0.40
    ZR
    0.40
    Estos
    0.40
    plots
    0.39
    POSITIVE LOGITS
     Classifier
    0.50
    यद
    0.45
     Holistic
    0.45
     differentiator
    0.45
    अन्य
    0.44
     productor
    0.42
     participan
    0.42
    शिष्ट
    0.42
     medico
    0.41
     zusätz
    0.41
    Activations Density 0.001%

    No Known Activations