© 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. 77806
    Prev
    Next
    INDEX
    Explanations

    non-english words and phrases

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

    translation

    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
    auk
    0.48
    ೆಯೇ
    0.46
    volumes
    0.46
     on
    0.46
    ဥ
    0.45
    ospheres
    0.45
    vira
    0.45
    wake
    0.45
    quasi
    0.45
    @@]
    0.44
    POSITIVE LOGITS
     Или
    0.53
     SE
    0.53
     कोशिका
    0.52
     सटे
    0.51
     Και
    0.50
    来说
    0.49
     ছিলাম
    0.49
     ແລະ
    0.48
    が好き
    0.48
     Что
    0.47
    Activations Density 0.000%

    No Known Activations