© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 241157
    Prev
    Next
    INDEX
    Explanations

    multilingual words

    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
    arati
    0.47
    awa
    0.46
    arat
    0.46
     blackened
    0.46
     darkened
    0.44
     لكل
    0.44
    fbox
    0.43
     l
    0.43
    anchi
    0.42
     acclimat
    0.42
    POSITIVE LOGITS
    다음
    0.51
     diret
    0.50
     নিন
    0.49
    其他
    0.48
     ise
    0.47
    𝑌
    0.46
     tomon
    0.46
     neh
    0.46
    この
    0.46
     dirigir
    0.46
    Activations Density 0.000%

    No Known Activations