© 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. 222832
    Prev
    Next
    INDEX
    Explanations

    multilingual words

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

    foreign languages

    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
    punctuation
    0.41
     correctly
    0.40
     minutes
    0.39
     чуть
    0.39
     motors
    0.38
    mén
    0.38
    p
    0.38
    tractor
    0.37
    常规
    0.37
    তোমার
    0.37
    POSITIVE LOGITS
     افر
    0.51
    ဆိုင်
    0.51
     மாண
    0.50
    ذر
    0.48
     sylvis
    0.48
     Trabal
    0.47
    學生
    0.46
     तयार
    0.46
     صاد
    0.46
    歷
    0.45
    Activations Density 0.001%

    No Known Activations