© 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. 147451
    Prev
    Next
    INDEX
    Explanations

    foreign language or non-english writing

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

    data, starting, magnesium

    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
    Negative Logits
     geometria
    0.49
     solidar
    0.47
    는
    0.45
     doble
    0.44
     leuke
    0.44
     solche
    0.43
     examen
    0.42
     defini
    0.42
     gehe
    0.42
     constru
    0.42
    POSITIVE LOGITS
    國
    0.47
    amounts
    0.46
    Ź
    0.45
     सांगतात
    0.45
    rtl
    0.44
    resultlist
    0.44
    aj
    0.43
    来到了
    0.43
    ZrO
    0.43
    cts
    0.42
    Activations Density 0.002%

    No Known Activations