© 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. 244408
    Prev
    Next
    INDEX
    Explanations

    foreign 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
    ath
    0.50
    ial
    0.44
     hxg
    0.44
     deciduous
    0.43
    会
    0.43
     甲
    0.42
    atha
    0.42
     河
    0.42
    ｅ
    0.42
     եւ
    0.41
    POSITIVE LOGITS
    Türkiye
    0.63
     víctima
    0.51
     сайте
    0.49
     opción
    0.49
     Nazionale
    0.47
     Israël
    0.47
    ເຄ
    0.47
     Израи
    0.46
     solução
    0.46
    Ҳ
    0.45
    Activations Density 0.001%

    No Known Activations